├── src ├── utils │ ├── __init__.py │ ├── __pycache__ │ │ ├── tools.cpython-39.pyc │ │ └── prompt_template.cpython-39.pyc │ ├── correlation.py │ ├── prompt_template.py │ └── tools.py ├── __pycache__ │ └── model.cpython-39.pyc ├── scripts │ ├── convert_data.py │ ├── get_score.py │ └── get_comparison.py ├── configs │ └── ds_config_zero3.json ├── model.py ├── inference.py └── finetune.py ├── figs ├── ind.png ├── comp.png ├── prompt.png ├── dataset.png └── overview.jpg ├── setup.py ├── requirements.txt ├── CONTRIBUTING.md ├── CODE_OF_CONDUCT.md ├── README.md ├── LICENSE └── data └── PerDOC.I.sample.jsonl /src/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /figs/ind.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/PerSE/HEAD/figs/ind.png -------------------------------------------------------------------------------- /figs/comp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/PerSE/HEAD/figs/comp.png -------------------------------------------------------------------------------- /figs/prompt.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/PerSE/HEAD/figs/prompt.png -------------------------------------------------------------------------------- /figs/dataset.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/PerSE/HEAD/figs/dataset.png -------------------------------------------------------------------------------- /figs/overview.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/PerSE/HEAD/figs/overview.jpg -------------------------------------------------------------------------------- /src/__pycache__/model.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/PerSE/HEAD/src/__pycache__/model.cpython-39.pyc -------------------------------------------------------------------------------- /src/utils/__pycache__/tools.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/PerSE/HEAD/src/utils/__pycache__/tools.cpython-39.pyc -------------------------------------------------------------------------------- /src/utils/__pycache__/prompt_template.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/facebookresearch/PerSE/HEAD/src/utils/__pycache__/prompt_template.cpython-39.pyc -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Meta Platforms, Inc. and affiliates. 2 | 3 | import os 4 | from setuptools import setup, find_packages 5 | 6 | setup(name='perse', version='0.1', packages=find_packages()) -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | sentencepiece==0.1.99 2 | torch==2.0.1 3 | pandas==2.0.3 4 | matplotlib==3.7.2 5 | scikit-learn==1.3.0 6 | wandb==0.15.8 7 | datasets==2.14.6 8 | numpy==1.24.4 9 | flask==2.3.2 10 | flask_cors==4.0.0 11 | daal==2023.2.1 12 | fire==0.5.0 13 | tokenizers==0.13.3 14 | deepspeed 15 | transformers[torch]==4.31.0 16 | -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | # Contributing to PerSE 2 | We want to make contributing to this project as easy and transparent as 3 | possible. 4 | 5 | ## Pull Requests 6 | We actively welcome your pull requests. 7 | 8 | 1. Fork the repo and create your branch from `main`. 9 | 2. If you've added code that should be tested, add tests. 10 | 3. If you've changed APIs, update the documentation. 11 | 4. Ensure the test suite passes. 12 | 5. Make sure your code lints. 13 | 6. If you haven't already, complete the Contributor License Agreement ("CLA"). 14 | 15 | ## Contributor License Agreement ("CLA") 16 | In order to accept your pull request, we need you to submit a CLA. You only need 17 | to do this once to work on any of Facebook's open source projects. 18 | 19 | Complete your CLA here: 20 | 21 | ## Issues 22 | We use GitHub issues to track public bugs. Please ensure your description is 23 | clear and has sufficient instructions to be able to reproduce the issue. 24 | 25 | Facebook has a [bounty program](https://www.facebook.com/whitehat/) for the safe 26 | disclosure of security bugs. In those cases, please go through the process 27 | outlined on that page and do not file a public issue. 28 | 29 | ## License 30 | By contributing to PerSE, you agree that your contributions will be licensed 31 | under the LICENSE file in the root directory of this source tree. -------------------------------------------------------------------------------- /src/scripts/convert_data.py: -------------------------------------------------------------------------------- 1 | import os 2 | import json 3 | import random 4 | 5 | import argparse 6 | 7 | random.seed(42) 8 | 9 | # python scripts/convert_data.py --input_file data/PerMPST.k3.sample.jsonl --output_file data/PerMPST.k3.src.json 10 | 11 | def get_options(): 12 | args = argparse.ArgumentParser() 13 | # data options 14 | args.add_argument("--input_file", type=str, default="data/input.json") 15 | args.add_argument("--output_file", type=str, default="output/") 16 | args.add_argument("--do_shuffle", type=bool, default=False) 17 | 18 | args = args.parse_args() 19 | return args 20 | 21 | if __name__ == '__main__': 22 | 23 | args = get_options() 24 | print(args) 25 | 26 | input_file = args.input_file 27 | output_file = args.output_file 28 | 29 | dataset = { 30 | "type": "text2text", 31 | "instances": [] 32 | } 33 | with open(args.input_file) as fin: 34 | for line in fin: 35 | data = json.loads(line) 36 | ex = { 37 | 'idx': data['idx'], 38 | 'input': data['prompt'][0], 39 | 'output': data['completion'] 40 | } 41 | 42 | dataset['instances'].append(ex) 43 | 44 | if args.do_shuffle: 45 | random.shuffle(dataset['instances']) 46 | 47 | print("Convert {} examples to {}".format(len(dataset['instances']), output_file)) 48 | json.dump(dataset, open(output_file, 'w')) 49 | 50 | 51 | 52 | 53 | -------------------------------------------------------------------------------- /src/configs/ds_config_zero3.json: -------------------------------------------------------------------------------- 1 | { 2 | "fp16": { 3 | "enabled": "auto", 4 | "loss_scale": 0, 5 | "loss_scale_window": 1000, 6 | "initial_scale_power": 16, 7 | "hysteresis": 2, 8 | "min_loss_scale": 1 9 | }, 10 | 11 | "optimizer": { 12 | "type": "AdamW", 13 | "params": { 14 | "lr": "auto", 15 | "betas": "auto", 16 | "eps": "auto", 17 | "weight_decay": "auto" 18 | } 19 | }, 20 | 21 | "scheduler": { 22 | "type": "WarmupLR", 23 | "params": { 24 | "warmup_min_lr": "auto", 25 | "warmup_max_lr": "auto", 26 | "warmup_num_steps": "auto" 27 | } 28 | }, 29 | 30 | "zero_optimization": { 31 | "stage": 3, 32 | "offload_optimizer": { 33 | "device": "cpu", 34 | "pin_memory": true 35 | }, 36 | "offload_param": { 37 | "device": "cpu", 38 | "pin_memory": true 39 | }, 40 | "overlap_comm": true, 41 | "contiguous_gradients": true, 42 | "sub_group_size": 1e9, 43 | "reduce_bucket_size": "auto", 44 | "stage3_prefetch_bucket_size": "auto", 45 | "stage3_param_persistence_threshold": "auto", 46 | "stage3_max_live_parameters": 1e9, 47 | "stage3_max_reuse_distance": 1e9, 48 | "stage3_gather_16bit_weights_on_model_save": true 49 | }, 50 | 51 | "gradient_accumulation_steps": "auto", 52 | "gradient_clipping": "auto", 53 | "steps_per_print": 2000, 54 | "train_batch_size": "auto", 55 | "train_micro_batch_size_per_gpu": "auto", 56 | "wall_clock_breakdown": false 57 | } -------------------------------------------------------------------------------- /src/utils/correlation.py: -------------------------------------------------------------------------------- 1 | from scipy.stats import spearmanr, pearsonr, kendalltau 2 | import numpy as np 3 | 4 | def calculate_correlation(pred_score, human_score): 5 | result = {'pearsonr': 0, 'spearmanr': 0, 'kendalltau': 0} 6 | assert len(pred_score) == len(human_score) 7 | print(len(pred_score)) 8 | 9 | pearsonr_res = pearsonr(pred_score, human_score) 10 | spearmanr_res = spearmanr(pred_score, human_score) 11 | kendalltau_res = kendalltau(pred_score, human_score) 12 | result['pearsonr'], result['pearsonr_status'] = pearsonr_res[0], pearsonr_res[1:] 13 | result['spearmanr'], result['spearmanr_status'] = spearmanr_res[0], spearmanr_res[1:] 14 | result['kendalltau'], result['kendalltau_status'] = kendalltau_res[0], kendalltau_res[1:] 15 | 16 | match = (pred_score == human_score).sum() 17 | accu = match / len(pred_score) 18 | result['accu'] = accu 19 | 20 | return result 21 | 22 | def compute_metric(expected, labels): 23 | tp = np.sum(labels[expected == 1]) 24 | fp = np.sum(labels[expected == 0]) 25 | tn = np.sum(1-labels[expected == 0]) 26 | fn = np.sum(1-labels[expected == 1]) 27 | tpr = tp/(tp+fn) 28 | fpr = fp/(fp+tn) 29 | error_rate = (fp+fn)/(tp+fp+tn+fn) 30 | accuracy = (tp+tn)/(tp+fp+tn+fn) 31 | precision = tp/(tp+fp) 32 | recall = tp/(tp+fn) 33 | 34 | return { 35 | "tpr": tpr, 36 | "fpr": fpr, 37 | "error_rate": error_rate, 38 | "accuracy": accuracy, 39 | "precision": precision, 40 | "recall": recall 41 | } 42 | 43 | 44 | if __name__ == "__main__": 45 | pred_score = [0,0,0,0,1,0,0,1,0,0,0,0,0,1,0,1,1,1,0,1,1] 46 | human_score = [1,1,1,1,0,0,0,1,1,0,1,0,1,1,0,1,1,1,0,1,1] 47 | result = calculate_correlation(pred_score, human_score) 48 | print(result) -------------------------------------------------------------------------------- /src/model.py: -------------------------------------------------------------------------------- 1 | 2 | import os 3 | import re 4 | import json 5 | 6 | from tqdm import tqdm 7 | from typing import Iterable, List 8 | 9 | import numpy as np 10 | 11 | import torch 12 | import transformers 13 | from transformers import AutoModelForCausalLM, AutoTokenizer 14 | 15 | 16 | MAX_TARGET_LENGTH = 512 17 | 18 | class PerSE(): 19 | def __init__(self, model_name_or_path: str = "meta-llama/Llama-2-7b-hf", padding_side: str = "left", device: str = "cuda"): 20 | super().__init__() 21 | self.device = device 22 | 23 | print(model_name_or_path) 24 | self.tokenizer = AutoTokenizer.from_pretrained( 25 | model_name_or_path, 26 | padding_side=padding_side, 27 | use_fast=False, 28 | ) 29 | self.model = AutoModelForCausalLM.from_pretrained(model_name_or_path).to(device) 30 | 31 | print("Vocab Size: ", len(self.tokenizer)) 32 | print("Loaded in model and tokenizer!") 33 | 34 | self.model.train() 35 | 36 | def inference(self, prompts: List, batch_size: int = 1, **kwargs) -> Iterable[str]: 37 | self.model.eval() 38 | 39 | results = [] 40 | chunk_num = len(prompts) // batch_size + (len(prompts) % batch_size > 0) 41 | scope = tqdm(range(chunk_num)) if chunk_num > 10 else range(chunk_num) 42 | with torch.no_grad(): 43 | for i in scope: 44 | batch_x = prompts[i*batch_size:(i+1)*batch_size] 45 | inputs = self.tokenizer(batch_x, return_tensors="pt", padding=True, truncation=True).to(self.device) 46 | prompt_len = inputs.input_ids.shape[1] 47 | outputs = self.model.generate(**inputs, **kwargs) 48 | outputs = outputs[:,prompt_len:] 49 | res = self.tokenizer.batch_decode(outputs, skip_special_tokens=True) 50 | results.extend(res) 51 | return results -------------------------------------------------------------------------------- /src/utils/prompt_template.py: -------------------------------------------------------------------------------- 1 | SCORE_SYSTEM_PROMPT="You function as an insightful assistant whose role is to assist individuals in making decisions that align with their personal preferences. Use your understanding of their likes, dislikes, and inclinations to provide relevant and thoughtful recommendations." 2 | SCORE_PROBLEM_PROMPT_TEMPLATE="""[User Question] You will be presented with several plot summaries, each accompanied by a review from the same critic. Your task is to analyze both the plot summaries and the corresponding reviews to discern the reviewer's preferences. Afterward, consider a new plot and create a review that you believe this reviewer would write based on the established preferences. 3 | 4 | {icl_example} 5 | 6 | Please follow the above critic and give a review for the given plot. Your response should strictly follow the format: 7 | ```json 8 | {{ 9 | "Review": "", 10 | "Score": <1-10, 1 is the lowest and 10 is the highest> 11 | }} 12 | ``` 13 | Please remember to replace the placeholder text within the "<>" with the appropriate details of your response. 14 | 15 | [The Start of Plot] 16 | {plot} 17 | [The End of Plot] 18 | """ 19 | 20 | SCORE_CASE_TEMPLATE="""[The Start of Plot {n}] 21 | {plot} 22 | [The End of Plot {n}] 23 | [Review] 24 | ```json 25 | {{ 26 | "Review": "{review}", 27 | "Score": {score} 28 | }} 29 | ``` 30 | """ 31 | 32 | 33 | 34 | RANK_SYSTEM_PROMPT="You function as an insightful assistant whose role is to assist individuals in making decisions that align with their personal preferences. Use your understanding of their likes, dislikes, and inclinations to provide relevant and thoughtful recommendations." 35 | RANK_PROBLEM_PROMPT_TEMPLATE="""[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference: 36 | 37 | [The Start of User Preference] 38 | {icl_example} 39 | [The End of User Preference] 40 | 41 | [User Question] Based on the above user preference, compare the following two plots: 42 | 43 | [The Start of Plot A] 44 | {plan1} 45 | [The End of Plot A] 46 | 47 | [The Start of Plot B] 48 | {plan2} 49 | [The End of Plot B] 50 | 51 | The response should use this specific format: 52 | ```json 53 | {{ 54 | "Choice": <"Plot A" or "Plot B" or "N/A">, 55 | }} 56 | ``` 57 | Please remember to replace the placeholder text within the "<>" with the appropriate details of your response. 58 | """ 59 | 60 | RANK_CASE_TEMPLATE="""[The Start of Plot A] 61 | {plan1} 62 | [The End of Plot A] 63 | [The Start of Plot B] 64 | {plan2} 65 | [The End of Plot B] 66 | [Response] 67 | {completion} 68 | """ 69 | 70 | RANK_COMPLETION = """```json 71 | {{ 72 | "Choice": "{choice}", 73 | }} 74 | ```""" -------------------------------------------------------------------------------- /src/scripts/get_score.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | import json 4 | import fire 5 | 6 | import re 7 | import ast 8 | 9 | import pandas as pd 10 | 11 | 12 | from utils.correlation import calculate_correlation 13 | from utils.tools import check_json 14 | 15 | DEBUG=False 16 | 17 | def check_review(response): 18 | if not isinstance(response, str): 19 | return False, None 20 | if response.startswith('"Review"'): 21 | response = "```json{" + response 22 | 23 | status, content = check_json(response) 24 | 25 | if status == False: 26 | return False, content 27 | 28 | if not isinstance(content, dict) or 'Review' not in content.keys() or 'Score' not in content.keys(): 29 | return False, None 30 | if not isinstance(content['Score'], int): 31 | return False, None 32 | 33 | content = content.replace("\n", '') if isinstance(content, str) else content 34 | 35 | return True, content 36 | 37 | 38 | def run(result_file, info_file, savename=None, max_num = -1): 39 | 40 | df_ = pd.read_json(result_file, orient='records', lines=True) 41 | info_df_ = pd.read_json(info_file, orient='records', lines=True) 42 | print('Ori Info:', info_df_.shape) 43 | 44 | if max_num > 0: 45 | df_ = df_[:max_num] 46 | print('Select Info:', df_.shape) 47 | 48 | info_df_['prompt_str'] = info_df_['prompt'].apply(lambda x:x[0].strip() if isinstance(x, list) else x.strip()) 49 | df_['prompt_str'] = df_['prompt'].apply(lambda x:x[0].strip() if isinstance(x, list) else x.strip()) 50 | info_df_ = info_df_.drop_duplicates('prompt_str') 51 | print('Info remove duplicate :', info_df_.shape) 52 | df_ = df_.drop_duplicates('prompt_str') 53 | print('Result remove duplicate :', df_.shape) 54 | 55 | info_df_['idx'] = range(0, len(info_df_)) 56 | df_all = pd.merge(info_df_, df_, on=['prompt_str']) 57 | print('Merge Info:', df_all.shape) 58 | df_all = df_all.drop(['prompt_x', 'prompt_y'], axis=1) 59 | 60 | for idx, value in df_all.iterrows(): 61 | status, refer = check_json(value['completion']) 62 | if status: 63 | df_all.at[idx, 'refer_score'] = refer['Score'] 64 | df_all.at[idx, 'refer_text'] = refer['Review'] 65 | else: 66 | df_all.at[idx, 'refer_score'] = -1 67 | if DEBUG: 68 | print("Refer", idx) 69 | print(value['completion']) 70 | 71 | status, hypo = check_json(value['response']) 72 | if status: 73 | df_all.at[idx, 'hypo_score'] = hypo['Score'] 74 | df_all.at[idx, 'hypo_text'] = hypo['Review'] 75 | else: 76 | df_all.at[idx, 'hypo_score'] = -1 77 | df_all.at[idx, 'hypo_text'] = value['response'] 78 | if DEBUG: 79 | print("Hypo", idx) 80 | print(value['response']) 81 | 82 | if savename != None: 83 | print(f'Save to {savename}') 84 | df_all.to_csv(savename) 85 | 86 | human = df_all[df_all['hypo_score'] != -1]['refer_score'].values 87 | pred = df_all[df_all['hypo_score'] != -1]['hypo_score'].values 88 | 89 | res = calculate_correlation(pred_score=pred, human_score=human) 90 | print(res) 91 | 92 | return 93 | 94 | # python get_score.py --result_file results/version.jsonl --info_file review.valid.c1 --savename logs/version.result.csv 95 | 96 | if __name__ == "__main__": 97 | fire.Fire(run) -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- 1 | # Code of Conduct 2 | 3 | ## Our Pledge 4 | 5 | In the interest of fostering an open and welcoming environment, we as 6 | contributors and maintainers pledge to make participation in our project and 7 | our community a harassment-free experience for everyone, regardless of age, body 8 | size, disability, ethnicity, sex characteristics, gender identity and expression, 9 | level of experience, education, socio-economic status, nationality, personal 10 | appearance, race, religion, or sexual identity and orientation. 11 | 12 | ## Our Standards 13 | 14 | Examples of behavior that contributes to creating a positive environment 15 | include: 16 | 17 | * Using welcoming and inclusive language 18 | * Being respectful of differing viewpoints and experiences 19 | * Gracefully accepting constructive criticism 20 | * Focusing on what is best for the community 21 | * Showing empathy towards other community members 22 | 23 | Examples of unacceptable behavior by participants include: 24 | 25 | * The use of sexualized language or imagery and unwelcome sexual attention or 26 | advances 27 | * Trolling, insulting/derogatory comments, and personal or political attacks 28 | * Public or private harassment 29 | * Publishing others' private information, such as a physical or electronic 30 | address, without explicit permission 31 | * Other conduct which could reasonably be considered inappropriate in a 32 | professional setting 33 | 34 | ## Our Responsibilities 35 | 36 | Project maintainers are responsible for clarifying the standards of acceptable 37 | behavior and are expected to take appropriate and fair corrective action in 38 | response to any instances of unacceptable behavior. 39 | 40 | Project maintainers have the right and responsibility to remove, edit, or 41 | reject comments, commits, code, wiki edits, issues, and other contributions 42 | that are not aligned to this Code of Conduct, or to ban temporarily or 43 | permanently any contributor for other behaviors that they deem inappropriate, 44 | threatening, offensive, or harmful. 45 | 46 | ## Scope 47 | 48 | This Code of Conduct applies within all project spaces, and it also applies when 49 | an individual is representing the project or its community in public spaces. 50 | Examples of representing a project or community include using an official 51 | project e-mail address, posting via an official social media account, or acting 52 | as an appointed representative at an online or offline event. Representation of 53 | a project may be further defined and clarified by project maintainers. 54 | 55 | This Code of Conduct also applies outside the project spaces when there is a 56 | reasonable belief that an individual's behavior may have a negative impact on 57 | the project or its community. 58 | 59 | ## Enforcement 60 | 61 | Instances of abusive, harassing, or otherwise unacceptable behavior may be 62 | reported by contacting the project team at . All 63 | complaints will be reviewed and investigated and will result in a response that 64 | is deemed necessary and appropriate to the circumstances. The project team is 65 | obligated to maintain confidentiality with regard to the reporter of an incident. 66 | Further details of specific enforcement policies may be posted separately. 67 | 68 | Project maintainers who do not follow or enforce the Code of Conduct in good 69 | faith may face temporary or permanent repercussions as determined by other 70 | members of the project's leadership. 71 | 72 | ## Attribution 73 | 74 | This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4, 75 | available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html 76 | 77 | [homepage]: https://www.contributor-covenant.org 78 | 79 | For answers to common questions about this code of conduct, see 80 | https://www.contributor-covenant.org/faq -------------------------------------------------------------------------------- /src/scripts/get_comparison.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | import json 4 | import fire 5 | 6 | import re 7 | import ast 8 | 9 | import pandas as pd 10 | 11 | from utils.tools import check_json 12 | from utils.correlation import calculate_correlation 13 | 14 | DEBUG=False 15 | 16 | def check_json(response): 17 | status, content = check_json(response) 18 | 19 | if status == False: 20 | response = '""' + content + '""' 21 | try: 22 | content = json.loads(response) 23 | except: 24 | return False, content 25 | 26 | return True, content 27 | 28 | def format_answer(x): 29 | if x == 'Plot A': 30 | return 0 31 | elif x == 'Plot B': 32 | return 1 33 | elif x== 'N/A': 34 | return 2 35 | else: 36 | return -1 37 | 38 | def get_results(data): 39 | query = sorted([k for k in data.keys() if k[:2] in ['Q1','Q3','Q4','Q5','Q6']]) 40 | results = [] 41 | for k in query: 42 | if k in data: 43 | results.append(format_answer(data[k])) 44 | else: 45 | results.append(-1) 46 | return results 47 | 48 | 49 | def run(result_file, info_file, savename=None, max_num = -1): 50 | 51 | df_ = pd.read_json(result_file, orient='records', lines=True) 52 | info_df_ = pd.read_json(info_file, orient='records', lines=True) 53 | print('Ori Info:', info_df_.shape) 54 | 55 | if max_num > 0: 56 | df_ = df_[:max_num] 57 | print('Select Info:', df_.shape) 58 | 59 | info_df_['prompt_str'] = info_df_['prompt'].apply(lambda x:x[0].strip() if isinstance(x, list) else x.strip()) 60 | df_['prompt_str'] = df_['prompt'].apply(lambda x:x[0].strip() if isinstance(x, list) else x.strip()) 61 | 62 | info_df_ = info_df_.drop_duplicates('prompt_str') 63 | print('Info remove duplicate :', info_df_.shape) 64 | df_ = df_.drop_duplicates('prompt_str') 65 | print('Result remove duplicate :', df_.shape) 66 | 67 | 68 | info_df_['idx'] = range(0, len(info_df_)) 69 | df_all = pd.merge(info_df_, df_, on=['prompt_str']) 70 | print('Merge Info:', df_all.shape) 71 | df_all = df_all.drop(['prompt_x', 'prompt_y'], axis=1) 72 | 73 | for idx, value in df_all.iterrows(): 74 | status, refer = check_json(value['completion']) 75 | if status and 'Choice' in refer.keys(): 76 | results = format_answer(refer['Choice']) 77 | df_all.loc[idx, 'refer_score'] = results 78 | else: 79 | df_all.loc[idx, 'refer_score'] = -1 80 | if DEBUG: 81 | print("==============Refer==============") 82 | print(value['completion']) 83 | 84 | status, hypo = check_json(value['response']) 85 | if status and isinstance(hypo, dict) and 'Choice' in hypo.keys(): 86 | results = format_answer(hypo['Choice']) 87 | df_all.loc[idx, 'hypo_score'] = results 88 | else: 89 | df_all.loc[idx, 'hypo_score'] = -1 90 | if DEBUG: 91 | print("==============Hypo==============") 92 | print(value['response']) 93 | print(check_json(value['response'])) 94 | 95 | 96 | if savename != None: 97 | print(f'Save to {savename}') 98 | df_all.to_csv(savename) 99 | 100 | if 'aspect' in df_all.columns: 101 | for name, df in df_all.groupby('aspect'): 102 | human = df[df['hypo_score'] != -1]['refer_score'].values 103 | pred = df[df['hypo_score'] != -1]['hypo_score'].values 104 | res = calculate_correlation(pred_score=pred, human_score=human) 105 | print(f'{name}\t',res) 106 | 107 | human = df_all[df_all['hypo_score'] != -1]['refer_score'].values 108 | pred = df_all[df_all['hypo_score'] != -1]['hypo_score'].values 109 | 110 | res = calculate_correlation(pred_score=pred, human_score=human) 111 | print(res) 112 | 113 | return 114 | 115 | # python get_comparison.py --result_file results/version.jsonl --info_file annotation.valid.Q1 --savename logs/version.result.csv 116 | 117 | if __name__ == "__main__": 118 | fire.Fire(run) 119 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # PerSE 2 | This is the repository for the paper: *Learning Personalized Story Evaluation*. 3 | 4 | ![PerSE](figs/overview.jpg) 5 | 6 | ## Personalized Story Evaluation Dataset 7 | We re-purpose two story datasets for personalized story evaluation: **PerMPST** and **PerDOC**. 8 | 9 | * **PerMPST**: Each example consists of several annotated reviews (k = 1 to 5) from the same reviewer and a new plot to be evaluated. Each annotated review includes anonymized and summarized moive plot, a detailed review text, and a score (from 1 to 10, 1 is the lowest). 10 | * **PerDOC**: Each example consists for one annotated review and a new paired story to be evaluated. The annotated review includes two story plots derived from the same premise, personalized comparison results on five aspects (*Interestingness*, *Adaptability*, *Surprise*, *Character Development* and *Ending*). 11 | 12 | 13 | The dataset statistic is listed below. More detailed information can be found in the paper and appendix. 14 | We provide several examples in *data/* directory, and the full dataset will be available in [PerMPST](https://dl.fbaipublicfiles.com/perse/PerMPST.tar.gz) and [PerDoc](https://dl.fbaipublicfiles.com/perse/PerDOC.tar.gz). 15 | 16 | ![Dataset](figs/dataset.png) 17 | 18 | 19 | ## Personalized Story Evaluation Model (PerSE) 20 | We develop **Per**sonalized **S**tory **E**valuation model (**PerSE**) to provide reviewer-specific evaluation on stories. It can provide a detailed review and a score (1-10) for one individual story, or compare two stories on five fine-grained aspects (*Interestingness*, *Adaptability*, *Surprise*, *Character Development* and *Ending*). 21 | 22 | It is instrution tuned from [LLaMA-2](https://github.com/facebookresearch/llama) using the following prompt format: 23 | 24 | ![Prompt](figs/prompt.png) 25 | 26 | ### Setup 27 | 28 | We recommand using conda environment to set up. 29 | ```shell 30 | $ conda create -n perse python=3.9 31 | $ conda activate perse 32 | $ pip install -r requirements.txt 33 | $ pip install -e . 34 | ``` 35 | 36 | Before start, download PerMPST and PerDOC from the provided links. We provide `src/scripts/convert_data.py` to convert the original dataset to the training format. For example, to convert the sample data, the command is: 37 | 38 | ``` shell 39 | $ cd src 40 | $ python scripts/convert_data.py --input_file ../data/PerMPST.k3. 41 | sample.jsonl --output_file ../data/PerMPST.k3.src.json 42 | ``` 43 | Then *PerMPST.k3.src.json* can be used for the training. For inference, we do not need to covert the data. 44 | 45 | ### Training 46 | 47 | We use deepspeed to speed up the training phase. The config file for deepspeed is `src/configs/ds_config_zero3.json`. We use 8 x 80G A100 GPU for training, set the batch size to 4 and learning rate to 1e-5. More options can be found in `src/finetune.py`. The training command should be something like: 48 | 49 | ``` shell 50 | $ cd src 51 | $ deepspeed --num_gpus 8 finetune.py --data_file ../data/PerMPST.k3.src.json --save_dir ../checkpoints/ 52 | ``` 53 | 54 | ### Inference 55 | 56 | We provide two modes for interence. One is to evaluate the test set (**evaluate**) and the other is to receive command line input (**interactive**). We refer readers to `src/inference.py` for detailed information. For evaluation, a typical inference command is: 57 | 58 | ``` shell 59 | $ cd src 60 | $ python inference.py --input_file ../data/PerMPST.k3.sample.jsonl --ckpt checkponints/checkpoint-10 61 | ``` 62 | 63 | ### Others 64 | 65 | We provide several scripts for post-process and to calculate the correlation. Please check `scripts/get_comparison.py` and `get_score.py` for more information. 66 | 67 | ### Results 68 | 69 | **Individual Story Evaluation on PerMPST** 70 | The results are the correlation between the human rating and the model prediction. 71 | ![Individual Story Evaluation](figs/ind.png) 72 | 73 | 74 | **Fine-grained Comparative Evaluation on PerDOC** 75 | The results are the prediction accuracy between the human label and the model prediction. 76 | ![Fine-grained Story Evaluation](figs/comp.png) -------------------------------------------------------------------------------- /src/utils/tools.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | 4 | import re 5 | import ast 6 | import json 7 | 8 | def load_json(path, index): 9 | start, end = None, None 10 | if index != "-1": 11 | parts = index.split('-') 12 | if len(parts) == 1: 13 | point = int(parts[0]) 14 | start, end = point, point+1 15 | else: 16 | start, end = int(parts[0]), int(parts[1]) 17 | print(f"Start: {start}, End: {end}") 18 | 19 | if os.path.isdir(path): 20 | data = [] 21 | 22 | if start is None or end is None: 23 | files = [x for x in os.listdir(path) if x.endswith('.json')] 24 | start, end = 0, len(files) 25 | print(f"Start: {start}, End: {end}") 26 | 27 | for i in range(start, end): 28 | file = os.path.join(path, f'{i}.json') 29 | data.append(json.load(open(file))) 30 | 31 | return data, start, end 32 | 33 | else: 34 | 35 | if path.endswith('jsonl'): 36 | data = [json.loads(x) for x in open(path)] 37 | else: 38 | data = json.load(open(path)) 39 | 40 | if start is None or end is None: 41 | start, end = 0, len(data) 42 | print(f"Start: {start}, End: {end}") 43 | return data[start:end], start, end 44 | 45 | 46 | 47 | 48 | def get_valid_entry(content): 49 | try: 50 | valid_entry = ast.literal_eval('[' + content +']') 51 | except: 52 | key_value_pattern = r'([^:]+):(("[^"]+")|([^,]+)),?' 53 | 54 | valid_entry = {} 55 | for x in re.findall(key_value_pattern, content): 56 | key = x[0].strip().lstrip('{') 57 | value = x[1].strip().rstrip(';').rstrip('}') 58 | xx = '{' + key + ':' + value + '}' 59 | try: 60 | xx = ast.literal_eval(xx) 61 | if isinstance(xx, dict): 62 | valid_entry.update(xx) 63 | except: 64 | continue 65 | return valid_entry 66 | 67 | 68 | def check_json(response): 69 | response = response.replace('\n', '').replace('\r', '') 70 | response = response.replace(" ", "") 71 | code_env = r'```([\s\S]*?)```' 72 | match_content = re.findall(code_env, response) 73 | if match_content != []: 74 | response = match_content[-1].lstrip('json').lstrip('css').lstrip('javascript').lstrip('vbnet') 75 | response = response.replace(': "', ':@').replace('","Sco', '@,"Sco').replace('"', "'").replace('@', '"') 76 | else: 77 | json_env = r'({([\s\S]*?)}+)' 78 | match_content = re.findall(json_env, response) 79 | if match_content != []: 80 | response = match_content[-1][0] 81 | 82 | 83 | try: 84 | content = ast.literal_eval(response) 85 | response = json.dumps(content) 86 | except: 87 | repaired_response = response 88 | json_env = r'{([\s\S]*?)}' 89 | inner_content = response.strip()[1:-1] 90 | for x in re.findall(json_env, inner_content): 91 | xx = x.strip() 92 | valid_entries = get_valid_entry(xx) 93 | valid_str = json.dumps(valid_entries) 94 | repaired_response = response.replace('{'+x+'}', valid_str) 95 | response = repaired_response 96 | 97 | try: 98 | content = json.loads(response) 99 | except: 100 | return False, response 101 | 102 | return True, content 103 | 104 | 105 | 106 | def clean_plot(plot): 107 | sentences = plot.split("\n") 108 | sentences = [x.strip() for x in sentences] 109 | if sentences[0].startswith('*'): 110 | sentences = [x for x in sentences if x.startswith('*')] 111 | if sentences[0].startswith('-'): 112 | sentences = [x for x in sentences if x.startswith('-')] 113 | content = "\n".join(sentences).strip() 114 | end_idx = content.rfind('.') 115 | content = content[:end_idx+1] 116 | return content 117 | 118 | def clean_review(review, maxlen=150): 119 | if review == '': 120 | return review 121 | review = review.replace('"','').replace("'","") 122 | review = review + '.' if not review.endswith('.') else review 123 | review = " ".join(review.split(' ')[:maxlen]) 124 | end_idx = review.rfind('.') 125 | review = review[:end_idx+1] 126 | return review 127 | 128 | 129 | def convert_messages_to_oasst_format(messages, message_end): 130 | prompt = '' 131 | for message in messages: 132 | if message['role'] == 'system': 133 | continue 134 | # prompt += '<|system|>' + message['content'] 135 | elif message['role'] == 'user': 136 | prompt += '<|prompter|>' + message['content'] 137 | elif message['role'] == 'assistant': 138 | prompt += '<|assistant|>' + message['content'] 139 | if messages[-1]['content'].endswith(message_end): 140 | if messages[-1]['role'] == 'user': 141 | prompt += '<|assistant|>' 142 | else: 143 | prompt += '<|prompter|>' 144 | return prompt 145 | 146 | 147 | def convert_messages_to_llama2_format(dialog, message_start='', message_end=''): 148 | B_INST, E_INST = "[INST]", "[/INST]" 149 | B_SYS, E_SYS = "<>\n", "\n<>\n\n" 150 | DEFAULT_SYSTEM_PROMPT = """You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.""" 151 | 152 | for d in dialog: 153 | d['content'] = d['content'].replace(message_start, "").replace(message_end, "") 154 | 155 | if dialog[0]["role"] != "system": 156 | dialog = [ 157 | { 158 | "role": "system", 159 | "content": DEFAULT_SYSTEM_PROMPT, 160 | } 161 | ] + dialog 162 | dialog = [ 163 | { 164 | "role": dialog[1]["role"], 165 | "content": B_SYS + dialog[0]["content"] + E_SYS + dialog[1]["content"], 166 | } 167 | ] + dialog[2:] 168 | 169 | assert all([msg["role"] == "user" for msg in dialog[::2]]) and all( 170 | [msg["role"] == "assistant" for msg in dialog[1::2]] 171 | ), ( 172 | "model only supports 'system', 'user' and 'assistant' roles, " 173 | "starting with 'system', then 'user' and alternating (u/a/u/a/u...)" 174 | ) 175 | 176 | 177 | if dialog[-1]["role"] != "user": 178 | print(f"Last message must be from user, got {dialog[-1]['role']}. Remove last message: {dialog[-1]}") 179 | dialog = dialog[:-1] 180 | 181 | prompts = "" 182 | for prompt, answer in zip(dialog[::2],dialog[1::2]): 183 | prompts += message_start + f"{B_INST} {(prompt['content']).strip()} {E_INST} {(answer['content']).strip()} " + message_end 184 | 185 | if len(dialog) % 2 == 1: 186 | prompts += message_start + f"{B_INST} {(dialog[-1]['content']).strip()} {E_INST}" 187 | 188 | return prompts 189 | -------------------------------------------------------------------------------- /src/inference.py: -------------------------------------------------------------------------------- 1 | import click 2 | import json 3 | import torch 4 | import argparse 5 | import os 6 | from tqdm.auto import tqdm 7 | from typing import Optional, Dict, Sequence 8 | import transformers 9 | 10 | from model import PerSE 11 | from utils.tools import clean_plot, clean_review, convert_messages_to_oasst_format, convert_messages_to_llama2_format 12 | from utils.prompt_template import ( 13 | SCORE_SYSTEM_PROMPT, 14 | SCORE_PROBLEM_PROMPT_TEMPLATE, 15 | SCORE_CASE_TEMPLATE, 16 | RANK_SYSTEM_PROMPT, 17 | RANK_PROBLEM_PROMPT_TEMPLATE, 18 | RANK_CASE_TEMPLATE, 19 | RANK_COMPLETION 20 | ) 21 | 22 | 23 | MAX_SOURCE_LENGTH = 4096 24 | MAX_TARGET_LENGTH = 512 25 | print("Max source length: ", MAX_SOURCE_LENGTH) 26 | print("MAX target length: ", MAX_TARGET_LENGTH) 27 | 28 | model_server_message_end = '' 29 | 30 | 31 | def get_input(): 32 | mode = input("Choose your mode (score / rank / quit): ") 33 | while mode not in ["score", "rank", "quit"]: 34 | mode = input("Rechoose your mode (score / rank / quit): ") 35 | if mode == "score": 36 | n = input("Please input the number of reviews you have to infer your preference (1-5): ") 37 | while not n.isnumeric() or eval(n) < 1 or eval(n) > 5: 38 | n = input("Please reinput the number of reviews you have to infer your preference (1-5): ") 39 | preference = [] 40 | n = eval(n) 41 | for i in range(n): 42 | plot = input(f"[Preference {i}] Please input the plot: ") 43 | review = input(f"[Preference {i}] Please input your review: ") 44 | score = input(f"[Preference {i}] Please input your score: ") 45 | ex = { 46 | 'plot': plot, 47 | 'review': review, 48 | 'score': score 49 | } 50 | preference.append(ex) 51 | plot = input(f"[Predict] Please input the new plot to be predicted: ") 52 | return mode, preference, plot 53 | elif mode == 'rank': 54 | preference = [] 55 | plot1 = input(f"[Preference] Please input the plot A: ") 56 | plot2 = input(f"[Preference] Please input the plot B: ") 57 | choice = input(f"[Preference] select the preferred plot (plot A / plot B): ") 58 | ex = { 59 | 'plot1': plot1, 60 | 'plot2': plot2, 61 | 'choice': choice 62 | } 63 | preference.append(ex) 64 | plot1 = input(f"[Predict] Please input the new plot A to be predicted: ") 65 | plot2 = input(f"[Predict] Please input the new plot B to be predicted: ") 66 | return mode, preference, [plot1, plot2] 67 | else: 68 | return [], [], [] 69 | 70 | 71 | 72 | def check_input_format(mode, preference, plot): 73 | assert isinstance(preference, list) 74 | if mode == 'score': 75 | for x in preference: 76 | assert 'plot' in x.keys() and isinstance(x['plot'], str) 77 | assert 'review' in x.keys() and isinstance(x['review'], str) 78 | assert 'score' in x.keys() and isinstance(x['score'], str) and x['score'].isnumeric() 79 | assert isinstance(plot, str) 80 | elif mode == 'rank': 81 | x = preference[0] 82 | assert 'plot1' in x.keys() and isinstance(x['plot1'], str) 83 | assert 'plot2' in x.keys() and isinstance(x['plot2'], str) 84 | assert 'choice' in x.keys() and isinstance(x['choice'], str) 85 | assert isinstance(plot, list) and isinstance(plot[0], str) and isinstance(plot[1], str) 86 | else: 87 | raise NotImplementedError 88 | 89 | def make_prompt(mode, preference, plot, format_type="oasst"): 90 | check_input_format(mode, preference=preference, plot=plot) 91 | if mode == 'score': 92 | icl_content = "" 93 | for i,x in enumerate(preference): 94 | case = SCORE_CASE_TEMPLATE.format(n=i, plot=clean_plot(x['plot']), review=clean_review(x['review']), score=x['score']) 95 | icl_content += case + '\n' 96 | prompt = SCORE_PROBLEM_PROMPT_TEMPLATE.format(icl_example=icl_content, plot=clean_plot(plot)) 97 | messages = [{'role': 'system', 'content': SCORE_SYSTEM_PROMPT + model_server_message_end}, 98 | {'role': 'user', 'content': prompt + model_server_message_end}, 99 | {'role': 'assistant', 'content': '[Review] Here is the Json format of the review: '}] 100 | elif mode == 'rank': 101 | x = preference[0] 102 | icl_content = RANK_CASE_TEMPLATE.format(plan1=clean_plot(x['plot1']), plan2=clean_plot(x['plot2']), completion=RANK_COMPLETION.format(choice=x['choice'])) 103 | prompt = RANK_PROBLEM_PROMPT_TEMPLATE.format(icl_example=icl_content, plan1 = plot[0], plan2=plot[1]) 104 | messages = [{'role': 'system', 'content': RANK_SYSTEM_PROMPT + model_server_message_end}, 105 | {'role': 'user', 'content': prompt + model_server_message_end}, 106 | {'role': 'assistant', 'content': 'Here is a JSON response: '}] 107 | else: 108 | raise NotImplementedError 109 | 110 | 111 | if format_type == "oasst": 112 | flat_messages = convert_messages_to_oasst_format(messages, model_server_message_end) 113 | elif format_type == 'llama2': 114 | flat_messages = convert_messages_to_llama2_format(messages) 115 | else: 116 | flat_messages = prompt 117 | 118 | return flat_messages 119 | 120 | 121 | def get_options(): 122 | args = argparse.ArgumentParser() 123 | # data options 124 | args.add_argument("--mode", type=str, default='evaluate', choices=['evaluate', 'interactive']) 125 | args.add_argument("--input_file", type=str, default="../data/PerMPST.k3.sample.jsonl") 126 | args.add_argument("--save_file", type=str, default="../results/PerMPST.k3.result.jsonl") 127 | args.add_argument("--seed", type=int, default=42) 128 | 129 | # model options 130 | args.add_argument("--device", type=str, default="cuda") 131 | args.add_argument("--ckpt", type=str, default="output/checkpoint-217") 132 | args.add_argument("--batch_size", type=int, default=1) 133 | args.add_argument("--temperature", type=float, default=0.8) 134 | 135 | 136 | args = args.parse_args() 137 | return args 138 | 139 | 140 | # python inference.py --input_file ../data/PerMPST.k3.sample.jsonl --ckpt output/checkpoint-240 141 | 142 | 143 | if __name__ == "__main__": 144 | args = get_options() 145 | 146 | if args.mode == 'evaluate': 147 | data = [json.loads(line) for line in open(args.input_file)] 148 | prompts = [x['prompt'] if isinstance(x['prompt'], str) else x['prompt'][0] for x in data] 149 | elif args.mode == 'interactive': 150 | mode, preference, plot = get_input() 151 | if preference == [] and plot == []: 152 | exit() 153 | prompts = make_prompt(mode, preference, plot) 154 | print(prompts) 155 | prompts = [prompts] 156 | else: 157 | raise NotImplementedError 158 | 159 | # load model 160 | model = PerSE(model_name_or_path=args.ckpt, device="cuda") 161 | 162 | # inference 163 | print("Start inference for {} examples".format(len(prompts))) 164 | configs = { 165 | "max_new_tokens": MAX_TARGET_LENGTH, 166 | "do_sample": args.temperature > 0, 167 | "temperature": args.temperature 168 | } 169 | responses = model.inference(prompts, batch_size=args.batch_size, **configs) 170 | 171 | # save results 172 | with open(args.save_file, "w") as f: 173 | for p, r in zip(prompts, responses): 174 | res = { 175 | 'prompt': p, 176 | 'response': r 177 | } 178 | f.write(json.dumps(res) + "\n") 179 | -------------------------------------------------------------------------------- /src/finetune.py: -------------------------------------------------------------------------------- 1 | import os, sys 2 | import copy 3 | import json 4 | import click 5 | import datetime 6 | import argparse 7 | from typing import Dict, Sequence 8 | from dataclasses import dataclass 9 | 10 | import torch 11 | from torch.utils.data import Dataset 12 | from datasets import load_dataset 13 | 14 | 15 | import transformers 16 | from transformers import Trainer, TrainingArguments 17 | 18 | from model import PerSE 19 | 20 | KEY_TYPE = "type" 21 | KEY_INSTANCES = "instances" 22 | ds_config = "configs/ds_config_zero3.json" 23 | do_train = True 24 | IGNORE_INDEX = -100 25 | 26 | # max_length = 4096 27 | max_length = 2048 28 | 29 | model_name_or_path = "meta-llama/Llama-2-7b-hf" 30 | 31 | 32 | # deepspeed --num_gpus 4 finetune.py 33 | # deepspeed --master_port 61000 --include "localhost:3,4" finetune.py 34 | 35 | def get_options(): 36 | args = argparse.ArgumentParser() 37 | # data options 38 | args.add_argument("--data_file", type=str, default="../data/PerMPST.k3.src.json") 39 | args.add_argument("--save_dir", type=str, default="../checkpoints/") 40 | args.add_argument("--padding_strategy", type=str, default='right') 41 | 42 | args.add_argument("--seed", type=int, default=42) 43 | args.add_argument("--batch_size", type=int, default=4) 44 | args.add_argument("--lr", type=float, default=1e-5) 45 | args.add_argument('--max_steps', type=int, default=4000) 46 | args.add_argument('--save_total_limit', type=int, default=3) 47 | 48 | args.add_argument("--local_rank", type=int, default=-1) 49 | 50 | args = args.parse_args() 51 | return args 52 | 53 | 54 | class SupervisedDataset(Dataset): 55 | """Dataset for supervised fine-tuning.""" 56 | 57 | def __init__(self, tokenizer: transformers.PreTrainedTokenizer): 58 | super(SupervisedDataset, self).__init__() 59 | targets = [ 60 | f"{example['output']}{tokenizer.eos_token}" for example in raw_dataset 61 | ] 62 | data_dict = preprocess(raw_dataset["input"], targets, tokenizer) 63 | self.input_ids = data_dict["input_ids"] 64 | self.labels = data_dict["labels"] 65 | 66 | # print(len(self.input_ids), self.input_ids[0].size(), self.labels[0].size()) 67 | 68 | def __len__(self): 69 | return len(self.input_ids) 70 | 71 | def __getitem__(self, i) -> Dict[str, torch.Tensor]: 72 | return dict(input_ids=self.input_ids[i], labels=self.labels[i]) 73 | 74 | 75 | @dataclass 76 | class DataCollatorForSupervisedDataset(object): 77 | """Collate examples for supervised fine-tuning.""" 78 | 79 | tokenizer: transformers.PreTrainedTokenizer 80 | 81 | def __call__(self, instances: Sequence[Dict]) -> Dict[str, torch.Tensor]: 82 | # print(instances) 83 | input_ids, labels = tuple( 84 | [instance[key] for instance in instances] for key in ("input_ids", "labels") 85 | ) 86 | input_ids = torch.nn.utils.rnn.pad_sequence( 87 | input_ids, batch_first=True, padding_value=self.tokenizer.pad_token_id 88 | ) 89 | labels = torch.nn.utils.rnn.pad_sequence( 90 | labels, batch_first=True, padding_value=IGNORE_INDEX 91 | ) 92 | return dict( 93 | input_ids=input_ids, 94 | labels=labels, 95 | attention_mask=input_ids.ne(self.tokenizer.pad_token_id), 96 | ) 97 | 98 | 99 | def make_supervised_data_module(tokenizer: transformers.PreTrainedTokenizer) -> Dict: 100 | """Make dataset and collator for supervised fine-tuning.""" 101 | train_dataset = SupervisedDataset(tokenizer=tokenizer) 102 | data_collator = DataCollatorForSupervisedDataset(tokenizer=tokenizer) 103 | return dict( 104 | train_dataset=train_dataset, eval_dataset=None, data_collator=data_collator 105 | ) 106 | 107 | 108 | def preprocess(sources, targets, tokenizer): 109 | # remove pairs where at least one record is None 110 | examples = [s + t for s, t in zip(sources, targets)] 111 | examples_tokenized, sources_tokenized = [ 112 | _tokenize_fn(strings, tokenizer) for strings in (examples, sources) 113 | ] 114 | input_ids = examples_tokenized["input_ids"] 115 | labels = copy.deepcopy(input_ids) 116 | for label, source_len in zip(labels, sources_tokenized["input_ids_lens"]): 117 | label[:source_len] = IGNORE_INDEX 118 | return dict(input_ids=input_ids, labels=labels) 119 | 120 | 121 | def _tokenize_fn( 122 | strings: Sequence[str], tokenizer: transformers.PreTrainedTokenizer 123 | ) -> Dict: 124 | """Tokenize a list of strings.""" 125 | tokenized_list = [ 126 | tokenizer( 127 | text, 128 | return_tensors="pt", 129 | padding=False, 130 | max_length = max_length, 131 | truncation=True, 132 | ) 133 | for text in strings 134 | ] 135 | input_ids = labels = [tokenized.input_ids[0] for tokenized in tokenized_list] 136 | input_ids_lens = labels_lens = [ 137 | tokenized.input_ids.ne(tokenizer.pad_token_id).sum().item() 138 | for tokenized in tokenized_list 139 | ] 140 | return dict( 141 | input_ids=input_ids, 142 | labels=labels, 143 | input_ids_lens=input_ids_lens, 144 | labels_lens=labels_lens, 145 | ) 146 | 147 | if __name__ == '__main__': 148 | 149 | args = get_options() 150 | print(args) 151 | 152 | input_file = args.data_file 153 | output_dir = args.save_dir 154 | 155 | if not os.path.exists(output_dir): 156 | os.makedirs(output_dir) 157 | 158 | # sanity check over the fields of json file 159 | with open(input_file) as fin: 160 | json_data = json.load(fin) 161 | if KEY_TYPE not in json_data.keys(): 162 | raise ValueError( 163 | f'"{KEY_TYPE}" field must be specified for data, e.g.' 164 | "{\n" 165 | f' "{KEY_TYPE}: "text2text",\n' 166 | f' "{KEY_INSTANCES}": [\n' 167 | ' { "text": "Sentence 1: This is a sentence." }\n' 168 | ' { "text": "Sentence 2: This is another sentence." }\n' 169 | f" ]\n" 170 | "}" 171 | ) 172 | 173 | # Load the dataset using the HuggingFace dataset library 174 | extensions = "json" 175 | raw_dataset = load_dataset( 176 | extensions, 177 | data_files=[input_file], 178 | field=KEY_INSTANCES, 179 | split="train", 180 | token=None, 181 | ) 182 | 183 | print(raw_dataset) 184 | print(len(raw_dataset)) 185 | 186 | perse = PerSE(model_name_or_path=model_name_or_path, padding_side=args.padding_strategy) 187 | 188 | run_name = datetime.datetime.now().strftime("%Y%m%d_%H%M%S") 189 | data_module = make_supervised_data_module(tokenizer=perse.tokenizer) 190 | training_args = TrainingArguments( 191 | output_dir=output_dir, 192 | evaluation_strategy="no", 193 | per_device_train_batch_size=args.batch_size, 194 | gradient_accumulation_steps=4, 195 | learning_rate=args.lr, 196 | lr_scheduler_type="cosine", 197 | warmup_ratio=0, 198 | weight_decay=0, 199 | max_steps=args.max_steps, 200 | logging_strategy="steps", 201 | logging_first_step=True, 202 | logging_steps=10, 203 | save_strategy="steps", 204 | save_steps=500, 205 | save_total_limit=args.save_total_limit, 206 | load_best_model_at_end=False, 207 | seed=args.seed, 208 | run_name=run_name, 209 | greater_is_better=False, 210 | deepspeed=ds_config, 211 | log_on_each_node=False, 212 | fp16=False, 213 | bf16=True, 214 | tf32=False, 215 | ) # tf32=True -> only for A100 216 | 217 | print("Start the trainer") 218 | 219 | if do_train: 220 | trainer = Trainer( 221 | model=perse.model, 222 | args=training_args, 223 | train_dataset=data_module["train_dataset"], 224 | eval_dataset=None, 225 | tokenizer=perse.tokenizer, 226 | data_collator=data_module["data_collator"], 227 | # compute_metrics=data_module.compute_metrics, 228 | preprocess_logits_for_metrics=None, 229 | ) 230 | 231 | train_result = trainer.train() 232 | trainer.save_model() # Saves the tokenizer too for easy upload 233 | metrics = train_result.metrics 234 | 235 | trainer.log_metrics("train", metrics) 236 | trainer.save_metrics("train", metrics) 237 | # trainer.save_state() -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | # Attribution-NonCommercial 4.0 International 2 | 3 | > *Creative Commons Corporation (“Creative Commons”) is not a law firm and does not provide legal services or legal advice. Distribution of Creative Commons public licenses does not create a lawyer-client or other relationship. Creative Commons makes its licenses and related information available on an “as-is” basis. Creative Commons gives no warranties regarding its licenses, any material licensed under their terms and conditions, or any related information. Creative Commons disclaims all liability for damages resulting from their use to the fullest extent possible.* 4 | > 5 | > ### Using Creative Commons Public Licenses 6 | > 7 | > Creative Commons public licenses provide a standard set of terms and conditions that creators and other rights holders may use to share original works of authorship and other material subject to copyright and certain other rights specified in the public license below. The following considerations are for informational purposes only, are not exhaustive, and do not form part of our licenses. 8 | > 9 | > * __Considerations for licensors:__ Our public licenses are intended for use by those authorized to give the public permission to use material in ways otherwise restricted by copyright and certain other rights. Our licenses are irrevocable. Licensors should read and understand the terms and conditions of the license they choose before applying it. Licensors should also secure all rights necessary before applying our licenses so that the public can reuse the material as expected. Licensors should clearly mark any material not subject to the license. This includes other CC-licensed material, or material used under an exception or limitation to copyright. [More considerations for licensors](http://wiki.creativecommons.org/Considerations_for_licensors_and_licensees#Considerations_for_licensors). 10 | > 11 | > * __Considerations for the public:__ By using one of our public licenses, a licensor grants the public permission to use the licensed material under specified terms and conditions. If the licensor’s permission is not necessary for any reason–for example, because of any applicable exception or limitation to copyright–then that use is not regulated by the license. Our licenses grant only permissions under copyright and certain other rights that a licensor has authority to grant. Use of the licensed material may still be restricted for other reasons, including because others have copyright or other rights in the material. A licensor may make special requests, such as asking that all changes be marked or described. Although not required by our licenses, you are encouraged to respect those requests where reasonable. [More considerations for the public](http://wiki.creativecommons.org/Considerations_for_licensors_and_licensees#Considerations_for_licensees). 12 | 13 | ## Creative Commons Attribution-NonCommercial 4.0 International Public License 14 | 15 | By exercising the Licensed Rights (defined below), You accept and agree to be bound by the terms and conditions of this Creative Commons Attribution-NonCommercial 4.0 International Public License ("Public License"). To the extent this Public License may be interpreted as a contract, You are granted the Licensed Rights in consideration of Your acceptance of these terms and conditions, and the Licensor grants You such rights in consideration of benefits the Licensor receives from making the Licensed Material available under these terms and conditions. 16 | 17 | ### Section 1 – Definitions. 18 | 19 | a. __Adapted Material__ means material subject to Copyright and Similar Rights that is derived from or based upon the Licensed Material and in which the Licensed Material is translated, altered, arranged, transformed, or otherwise modified in a manner requiring permission under the Copyright and Similar Rights held by the Licensor. For purposes of this Public License, where the Licensed Material is a musical work, performance, or sound recording, Adapted Material is always produced where the Licensed Material is synched in timed relation with a moving image. 20 | 21 | b. __Adapter's License__ means the license You apply to Your Copyright and Similar Rights in Your contributions to Adapted Material in accordance with the terms and conditions of this Public License. 22 | 23 | c. __Copyright and Similar Rights__ means copyright and/or similar rights closely related to copyright including, without limitation, performance, broadcast, sound recording, and Sui Generis Database Rights, without regard to how the rights are labeled or categorized. For purposes of this Public License, the rights specified in Section 2(b)(1)-(2) are not Copyright and Similar Rights. 24 | 25 | d. __Effective Technological Measures__ means those measures that, in the absence of proper authority, may not be circumvented under laws fulfilling obligations under Article 11 of the WIPO Copyright Treaty adopted on December 20, 1996, and/or similar international agreements. 26 | 27 | e. __Exceptions and Limitations__ means fair use, fair dealing, and/or any other exception or limitation to Copyright and Similar Rights that applies to Your use of the Licensed Material. 28 | 29 | f. __Licensed Material__ means the artistic or literary work, database, or other material to which the Licensor applied this Public License. 30 | 31 | g. __Licensed Rights__ means the rights granted to You subject to the terms and conditions of this Public License, which are limited to all Copyright and Similar Rights that apply to Your use of the Licensed Material and that the Licensor has authority to license. 32 | 33 | h. __Licensor__ means the individual(s) or entity(ies) granting rights under this Public License. 34 | 35 | i. __NonCommercial__ means not primarily intended for or directed towards commercial advantage or monetary compensation. For purposes of this Public License, the exchange of the Licensed Material for other material subject to Copyright and Similar Rights by digital file-sharing or similar means is NonCommercial provided there is no payment of monetary compensation in connection with the exchange. 36 | 37 | j. __Share__ means to provide material to the public by any means or process that requires permission under the Licensed Rights, such as reproduction, public display, public performance, distribution, dissemination, communication, or importation, and to make material available to the public including in ways that members of the public may access the material from a place and at a time individually chosen by them. 38 | 39 | k. __Sui Generis Database Rights__ means rights other than copyright resulting from Directive 96/9/EC of the European Parliament and of the Council of 11 March 1996 on the legal protection of databases, as amended and/or succeeded, as well as other essentially equivalent rights anywhere in the world. 40 | 41 | l. __You__ means the individual or entity exercising the Licensed Rights under this Public License. Your has a corresponding meaning. 42 | 43 | ### Section 2 – Scope. 44 | 45 | a. ___License grant.___ 46 | 47 | 1. Subject to the terms and conditions of this Public License, the Licensor hereby grants You a worldwide, royalty-free, non-sublicensable, non-exclusive, irrevocable license to exercise the Licensed Rights in the Licensed Material to: 48 | 49 | A. reproduce and Share the Licensed Material, in whole or in part, for NonCommercial purposes only; and 50 | 51 | B. produce, reproduce, and Share Adapted Material for NonCommercial purposes only. 52 | 53 | 2. __Exceptions and Limitations.__ For the avoidance of doubt, where Exceptions and Limitations apply to Your use, this Public License does not apply, and You do not need to comply with its terms and conditions. 54 | 55 | 3. __Term.__ The term of this Public License is specified in Section 6(a). 56 | 57 | 4. __Media and formats; technical modifications allowed.__ The Licensor authorizes You to exercise the Licensed Rights in all media and formats whether now known or hereafter created, and to make technical modifications necessary to do so. The Licensor waives and/or agrees not to assert any right or authority to forbid You from making technical modifications necessary to exercise the Licensed Rights, including technical modifications necessary to circumvent Effective Technological Measures. For purposes of this Public License, simply making modifications authorized by this Section 2(a)(4) never produces Adapted Material. 58 | 59 | 5. __Downstream recipients.__ 60 | 61 | A. __Offer from the Licensor – Licensed Material.__ Every recipient of the Licensed Material automatically receives an offer from the Licensor to exercise the Licensed Rights under the terms and conditions of this Public License. 62 | 63 | B. __No downstream restrictions.__ You may not offer or impose any additional or different terms or conditions on, or apply any Effective Technological Measures to, the Licensed Material if doing so restricts exercise of the Licensed Rights by any recipient of the Licensed Material. 64 | 65 | 6. __No endorsement.__ Nothing in this Public License constitutes or may be construed as permission to assert or imply that You are, or that Your use of the Licensed Material is, connected with, or sponsored, endorsed, or granted official status by, the Licensor or others designated to receive attribution as provided in Section 3(a)(1)(A)(i). 66 | 67 | b. ___Other rights.___ 68 | 69 | 1. Moral rights, such as the right of integrity, are not licensed under this Public License, nor are publicity, privacy, and/or other similar personality rights; however, to the extent possible, the Licensor waives and/or agrees not to assert any such rights held by the Licensor to the limited extent necessary to allow You to exercise the Licensed Rights, but not otherwise. 70 | 71 | 2. Patent and trademark rights are not licensed under this Public License. 72 | 73 | 3. To the extent possible, the Licensor waives any right to collect royalties from You for the exercise of the Licensed Rights, whether directly or through a collecting society under any voluntary or waivable statutory or compulsory licensing scheme. In all other cases the Licensor expressly reserves any right to collect such royalties, including when the Licensed Material is used other than for NonCommercial purposes. 74 | 75 | ### Section 3 – License Conditions. 76 | 77 | Your exercise of the Licensed Rights is expressly made subject to the following conditions. 78 | 79 | a. ___Attribution.___ 80 | 81 | 1. If You Share the Licensed Material (including in modified form), You must: 82 | 83 | A. retain the following if it is supplied by the Licensor with the Licensed Material: 84 | 85 | i. identification of the creator(s) of the Licensed Material and any others designated to receive attribution, in any reasonable manner requested by the Licensor (including by pseudonym if designated); 86 | 87 | ii. a copyright notice; 88 | 89 | iii. a notice that refers to this Public License; 90 | 91 | iv. a notice that refers to the disclaimer of warranties; 92 | 93 | v. a URI or hyperlink to the Licensed Material to the extent reasonably practicable; 94 | 95 | B. indicate if You modified the Licensed Material and retain an indication of any previous modifications; and 96 | 97 | C. indicate the Licensed Material is licensed under this Public License, and include the text of, or the URI or hyperlink to, this Public License. 98 | 99 | 2. You may satisfy the conditions in Section 3(a)(1) in any reasonable manner based on the medium, means, and context in which You Share the Licensed Material. For example, it may be reasonable to satisfy the conditions by providing a URI or hyperlink to a resource that includes the required information. 100 | 101 | 3. If requested by the Licensor, You must remove any of the information required by Section 3(a)(1)(A) to the extent reasonably practicable. 102 | 103 | 4. If You Share Adapted Material You produce, the Adapter's License You apply must not prevent recipients of the Adapted Material from complying with this Public License. 104 | 105 | ### Section 4 – Sui Generis Database Rights. 106 | 107 | Where the Licensed Rights include Sui Generis Database Rights that apply to Your use of the Licensed Material: 108 | 109 | a. for the avoidance of doubt, Section 2(a)(1) grants You the right to extract, reuse, reproduce, and Share all or a substantial portion of the contents of the database for NonCommercial purposes only; 110 | 111 | b. if You include all or a substantial portion of the database contents in a database in which You have Sui Generis Database Rights, then the database in which You have Sui Generis Database Rights (but not its individual contents) is Adapted Material; and 112 | 113 | c. You must comply with the conditions in Section 3(a) if You Share all or a substantial portion of the contents of the database. 114 | 115 | For the avoidance of doubt, this Section 4 supplements and does not replace Your obligations under this Public License where the Licensed Rights include other Copyright and Similar Rights. 116 | 117 | ### Section 5 – Disclaimer of Warranties and Limitation of Liability. 118 | 119 | a. __Unless otherwise separately undertaken by the Licensor, to the extent possible, the Licensor offers the Licensed Material as-is and as-available, and makes no representations or warranties of any kind concerning the Licensed Material, whether express, implied, statutory, or other. This includes, without limitation, warranties of title, merchantability, fitness for a particular purpose, non-infringement, absence of latent or other defects, accuracy, or the presence or absence of errors, whether or not known or discoverable. Where disclaimers of warranties are not allowed in full or in part, this disclaimer may not apply to You.__ 120 | 121 | b. __To the extent possible, in no event will the Licensor be liable to You on any legal theory (including, without limitation, negligence) or otherwise for any direct, special, indirect, incidental, consequential, punitive, exemplary, or other losses, costs, expenses, or damages arising out of this Public License or use of the Licensed Material, even if the Licensor has been advised of the possibility of such losses, costs, expenses, or damages. Where a limitation of liability is not allowed in full or in part, this limitation may not apply to You.__ 122 | 123 | c. The disclaimer of warranties and limitation of liability provided above shall be interpreted in a manner that, to the extent possible, most closely approximates an absolute disclaimer and waiver of all liability. 124 | 125 | ### Section 6 – Term and Termination. 126 | 127 | a. This Public License applies for the term of the Copyright and Similar Rights licensed here. However, if You fail to comply with this Public License, then Your rights under this Public License terminate automatically. 128 | 129 | b. Where Your right to use the Licensed Material has terminated under Section 6(a), it reinstates: 130 | 131 | 1. automatically as of the date the violation is cured, provided it is cured within 30 days of Your discovery of the violation; or 132 | 133 | 2. upon express reinstatement by the Licensor. 134 | 135 | For the avoidance of doubt, this Section 6(b) does not affect any right the Licensor may have to seek remedies for Your violations of this Public License. 136 | 137 | c. For the avoidance of doubt, the Licensor may also offer the Licensed Material under separate terms or conditions or stop distributing the Licensed Material at any time; however, doing so will not terminate this Public License. 138 | 139 | d. Sections 1, 5, 6, 7, and 8 survive termination of this Public License. 140 | 141 | ### Section 7 – Other Terms and Conditions. 142 | 143 | a. The Licensor shall not be bound by any additional or different terms or conditions communicated by You unless expressly agreed. 144 | 145 | b. Any arrangements, understandings, or agreements regarding the Licensed Material not stated herein are separate from and independent of the terms and conditions of this Public License. 146 | 147 | ### Section 8 – Interpretation. 148 | 149 | a. For the avoidance of doubt, this Public License does not, and shall not be interpreted to, reduce, limit, restrict, or impose conditions on any use of the Licensed Material that could lawfully be made without permission under this Public License. 150 | 151 | b. To the extent possible, if any provision of this Public License is deemed unenforceable, it shall be automatically reformed to the minimum extent necessary to make it enforceable. If the provision cannot be reformed, it shall be severed from this Public License without affecting the enforceability of the remaining terms and conditions. 152 | 153 | c. No term or condition of this Public License will be waived and no failure to comply consented to unless expressly agreed to by the Licensor. 154 | 155 | d. Nothing in this Public License constitutes or may be interpreted as a limitation upon, or waiver of, any privileges and immunities that apply to the Licensor or You, including from the legal processes of any jurisdiction or authority. 156 | 157 | > Creative Commons is not a party to its public licenses. Notwithstanding, Creative Commons may elect to apply one of its public licenses to material it publishes and in those instances will be considered the “Licensor.” Except for the limited purpose of indicating that material is shared under a Creative Commons public license or as otherwise permitted by the Creative Commons policies published at [creativecommons.org/policies](http://creativecommons.org/policies), Creative Commons does not authorize the use of the trademark “Creative Commons” or any other trademark or logo of Creative Commons without its prior written consent including, without limitation, in connection with any unauthorized modifications to any of its public licenses or any other arrangements, understandings, or agreements concerning use of licensed material. For the avoidance of doubt, this paragraph does not form part of the public licenses. 158 | > 159 | > Creative Commons may be contacted at creativecommons.org -------------------------------------------------------------------------------- /data/PerDOC.I.sample.jsonl: -------------------------------------------------------------------------------- 1 | {"idx":6867,"review_id":"2AXHP9KWXZXG","prompt":["[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference:\n\n[The Start of User Preference]\n[The Start of Plot A]\nPremise A lonely and reclusive computer programmer discovers new software that can simulate lifelike dreams, but as he becomes increasingly addicted to the program, he begins to suspect that the dreams are not merely hallucinations, but a means to connect with a parallel universe.Settings The story is set in a futuristic city, with towering skyscrapers and a bustling population that is always on the go.Characters Rachel Price Rachel Price is 28 years old and is Benjamins coworker at a major tech company.Benjamin Wright Benjamin Wright is 30 years old and lives in a modest studio apartment on the outskirts of the city.Jack Brown Jack Brown is 32 years old and is a charismatic and charming software developer who created the dream simulation software that Benjamin becomes obsessed with.Outline Scene Characters 1. Benjamin Wright, a young and talented employee of a tech company, is searching for a solution to his struggles with insomnia and mental health. Scene Characters Benjamin Wrighta. Benjamin becomes increasingly reliant on the program, using it multiple times a night to escape his solitary existence and experience lifelike dreams about his favorite city landmarks. Scene a busy caf\u00e9 in the city, where Benjamin is surrounded by patrons who are conversing and interacting with one another. Characters Benjamin Wrightb. As his addiction to the program spirals out of control, Benjamin begins to observe discrepancies in his dreams, such as inconsistencies with the real world. Scene the dreamworld, where Benjamin is exploring a city that is slightly different from the real one. Characters Benjamin Wrightc. Following a particularly bizarre dream, Benjamin decides to investigate the issue further and realizes that the software interface hes been interacting with is not what he thought. Scene Benjamins apartment, where he is staring at the blinking cursor on his computer screen. Characters Benjamin Wright2. While experimenting with new software, Benjamin stumbles upon a dream simulation program, which he promptly installs to help him get some rest. Scene Characters Benjamin Wrighta. Benjamin contacts a software developer, Jack Brown, with inquiries about the program, and sets up an appointment with him to discuss its origins. Scene a modern skyscraper, where Benjamin is intimidated by Jacks charismatic personality. Characters Benjamin Wright, Jack Brownb. During their conversation, Jack admits that the dream simulation software was designed to allow users to tap into a parallel universe. Scene a dark and eerie laboratory, where Benjamin is surrounded by strange machines and computer screens. Characters Jack Brownc. Benjamin becomes increasingly suspicious of his interactions with Rachel and the rest of his team members, as well as his friends and family members, feeling that their existence may not be real. Scene a bustling city park, where Benjamin is walking and observing the people around him. Characters Benjamin Wright, Rachel Price3. But as he becomes increasingly addicted to the program, Benjamin begins to suspect that there is more to the dreams than meets the eye, and that they may be windows to a real and parallel universe. Scene Characters Benjamin Wrighta. Benjamin uncovers an anomaly in his latest dream simulation experience, causing him to question the programs influence in his life. Scene a city street, where Benjamin is walking and exploring the city. Characters Benjamin Wrightb. He decides to seek professional help and meets with a psychologist, who is skeptical of his claims but remains curious about the phenomenon. Scene a modern psychologists office, where Benjamin is sitting in a comfortable chair and speaking to the psychologist. Characters Benjamin Wrightc. The psychologist suggests they conduct a controlled experiment by monitoring Benjamins dreams through the software. Scene a futuristic laboratory, where Benjamin is lying on a bed with computer screens and wires attached to him. Characters Benjamin Wright.\n[The End of Plot A]\n[The Start of Plot B]\nPremise A lonely and reclusive computer programmer discovers new software that can simulate lifelike dreams, but as he becomes increasingly addicted to the program, he begins to suspect that the dreams are not merely hallucinations, but a means to connect with a parallel universe.Settings The story is set in a dystopian future where technology has advanced to the point where virtual reality is a common and popular form of entertainment.Characters Rebecca White Rebecca White is 28 years old, a former employee of a tech company who has been involved in shady research and development of mind-reading technology.Isaac Johnson Isaac Johnson is 55 years old, an eccentric and reclusive software developer who has created a new program that can simulate lifelike dreams.Ethan Taylor Ethan Taylor is 25 years old, a computer programmer with a genius mind but poor social skills.Outline Scene Characters 1. Ethan discovers Isaacs lifelike dream software and becomes addicted to it, believing it to be a way to escape his lonely and reclusive life. Scene Characters Isaac Johnson, Ethan Taylora. Ethan Taylor, a 25-year-old lonely and reclusive computer programmer, develops an obsession with a new software that can simulate lifelike dreams after discovering it. Scene the dream laboratory where Ethan discovers the software. Characters Ethan Taylorb. His addiction to the software starts to interfere with his daily life, causing him to neglect his friends and hygiene. Scene Ethans apartment where his friends confront him about his addiction. Characters Ethan Taylorc. As he continues to frequent the dream simulation software, he experiences haunting dreams of a beautiful woman who he believes is his soulmate. Scene the dream simulation software where Ethan interacts with the beautiful woman. Characters Ethan Taylor2. Rebecca tries to convince Ethan to join her in further developing the dream software for her own greedy and twisted ends, but he refuses. Scene Characters Rebecca White, Ethan Taylora. Rebecca first confronts Ethan about the potentials of the dream software and tries to recruit him into working together to further develop it. Scene the dream laboratory where Rebecca confronts Ethan. Characters Rebecca White, Ethan Taylorb. When Ethan doesnt show any interest in her proposition, Rebecca decides to take matters into her own hands and starts experimenting with the software for her own selfish reasons. Scene Rebeccas laboratory where she experiments with the software. Characters Rebecca White, Ethan Taylorc. Unbeknownst to Ethan, the beautiful woman he sees in his dreams is connected to Rebeccas efforts to exploit the software. Scene Rebeccas laboratory where she connects her own memories to the software. Characters Rebecca White, Ethan Taylor3. After becoming increasingly addicted and frequently using the dream software, Ethan starts to suspect that the dreams he experiences may not be mere hallucinations, but a means to connect with a parallel universe. Scene Characters Ethan Taylora. Ethan starts to wonder if the dreams he has experienced in the simulation software are simply hallucinations. Scene Ethans apartment where he is pondering his thoughts. Characters Ethan Taylorb. He researches the science of parallel universes, trying to understand whether his suspicions have any basis in reality or if he is just becoming more delusional. Scene Ethans office where he researches parallel universes. Characters Ethan Taylorc. When he discovers evidence to support his suspicions, including clues left behind in his dreams, Ethan becomes more determined to connect with this parallel universe. Scene the dream laboratory where Ethan discovers the clues. Characters Ethan Taylor.\n[The End of Plot B]\nHere is the JSON response.```json\n{\n \"Choice\": \"Plot B\",\n}\n```\n\n[The End of User Preference]\n\n[User Question] Based on the above user preference, compare the following two plots:\n\n[The Start of Plot A]\nPremise In a world where time travel is a reality, a brilliant physicist uncovers a shocking truth \u2013 in order to save the world from global warming, time travel has been invented far too late. How does her discovery unravel the future of time travel and the fate of humanity?Settings The story is set in a dystopian future where the world has been ravaged by the effects of global warming.Characters Erika Wilson Erika Wilson is 24 years old, a renowned time traveler and Olivias longtime friend and confidant.Jason Lee Jason Lee is 36 years old, a seasoned time traveler and mentor to Olivia and Erika.Victoria Lee Victoria Lee is 32 years old, a time traveler and Olivias close friend, with years of experience and a deep understanding of the risks and consequences of time travel.Maria Rodriguez Maria Rodriguez is 32 years old, a dedicated activist and Olivias love interest, a constant source of support and optimism in a bleak future.Olivia Thompson Olivia Thompson is 26 years old, a brilliant physicist and time traveler with a tragic past.Marcus Johnson Marcus Johnson is 55 years old, Olivias former mentor and the inventor of time travel, filled with regret and regret for his actions.Outline Scene Characters 1. The discovery that time travel was invented too late to save the world from global warming leaves Olivia struggling to come to terms with her findings. Scene Characters Olivia Thompsona. As she goes over the data, Olivia realizes that time travel was invented too late to prevent global warming. Scene Olivias laboratory. Characters Olivia Thompsonb. She struggles to process this new information and its implications for the future. Scene Olivias laboratory. Characters Olivia Thompsonc. Knowing the truth, but torn between what to do, Olivia confides in her closest friends and fellow time travelers Erika and Jason. Scene Olivias home. Characters Erika Wilson, Jason Lee, Olivia Thompson2. As she grapples with accepting the truth, Olivia confides in Erika and Jason, who both offer her support and advice to help her decide on the best course of action. Scene Characters Erika Wilson, Jason Lee, Olivia Thompsona. Olivia confides in Erika and Jason, who both offer her support and advice. Scene Olivias home. Characters Erika Wilson, Jason Lee, Olivia Thompsonb. They discuss the various options available to Olivia and the implications of each decision. Scene Olivias home. Characters Olivia Thompsonc. Olivia begins to understand the immense power that she possesses as a time traveler and resolves to make a difference. Scene Olivias home. Characters Olivia Thompson3. Olivia eventually decides to use her knowledge of the time travel technology to create a stable time loop that would allow her to alter the past and prevent global warming from happening in the first place. Scene Characters Olivia Thompsona. Olivia formulates a plan to use the time travel technology to change the past and prevent the devastating effects of global warming. Scene Olivias laboratory. Characters Olivia Thompsonb. She shares her plan with Jason, Erika, and other close friends, including Maria, Victoria, and Marcus. Scene Olivias laboratory. Characters Erika Wilson, Jason Lee, Victoria Lee, Maria Rodriguez, Marcus Johnsonc. Her friends provide crucial insight and support, helping Olivia to build a stable time loop and alter the past. Scene Olivias laboratory. Characters Olivia Thompson.\n[The End of Plot A]\n\n[The Start of Plot B]\nPremise In a world where time travel is a reality, a brilliant physicist uncovers a shocking truth \u2013 in order to save the world from global warming, time travel has been invented far too late. How does her discovery unravel the future of time travel and the fate of humanity?Settings The story is set in a futuristic metropolis that spans several continents, with a diverse population of humans and androids.Characters Alex Morgan Alex Morgan is 28 years old, an expert android engineer who has worked closely with Aelita on several time travel projects.Elise Anderson Elise Anderson is 28 years old, Aelitas close friend and confidante, who is also an expert in her field.Aelita Nguyen Aelita Nguyen is 28 years old, a passionate physicist who is obsessed with understanding the intricacies of time and space.Outline Scene Characters 1. Aelita discovers that the invention of time travel technology has occurred too late to save the world from global warmings worst effects. Scene Characters Aelita Nguyena. Aelita, after extensive research, finds evidence that time travel has been invented far too late to preserve human civilization from the devastating effects of global warming. Scene a futuristic metropolis. Characters Aelita Nguyenb. She shares her discovery with Alex Morgan and Elise Anderson, who are both shocked and troubled by Aelitas findings. Scene a futuristic metropolis. Characters Alex Morgan, Elise Anderson, Aelita Nguyenc. With the help of her colleagues, Aelita attempts to develop an alternative form of time travel, hoping to find a solution to the global warming problem before its too late. Scene a futuristic metropolis. Characters Aelita Nguyen2. As she delves deeper into her research, Aelita becomes convinced that the current uses of time travel are too limited, and that its true potential has yet to be realized. Scene Characters Aelita Nguyena. Aelita shares her plan to revolutionize time travel with her colleagues, hoping they will join her in her quest to utilize the technology for a larger, more impactful purpose. Scene a futuristic metropolis. Characters Aelita Nguyenb. Alex and Elise, intrigued by Aelitas ambition, agree to work with her to develop an advanced time travel system that can address global warming. Scene a futuristic metropolis. Characters Alex Morgan, Elise Anderson, Aelita Nguyenc. With renewed determination, Aelita and her team begin working tirelessly to create this new time travel system and develop a test prototype. Scene a futuristic metropolis. Characters Aelita Nguyen3. She presents her ideas for a more advanced time travel system to the Time Institute, but faces resistance from the institutions leadership, who fear the potential consequences of Aelitas proposed changes. Scene Characters Aelita Nguyena. Aelita presents her proposal for a new time travel system to the Time Institutes leadership, hoping to gain support for her research. Scene a futuristic metropolis. Characters Aelita Nguyenb. The leadership is skeptical of Aelitas ideas and refuses to fund her project, believing it to be too risky and potentially damaging to the time travel technology. Scene a futuristic metropolis. Characters Aelita Nguyenc. Aelita is forced to seek alternative sources of funding, reaching out to potential investors outside the Time Institute in order to continue her research. Scene a futuristic metropolis. Characters Aelita Nguyen.\n[The End of Plot B]\n\nThe response should use this specific format: \n```json\n{\n \"Choice\": <\"Plot A\" or \"Plot B\">,\n}\n```\nPlease remember to replace the placeholder text within the \"<>\" with the appropriate details of your response.\n\n [Response]"],"completion":"```json\n{\n \"Choice\": \"Plot B\",\n}\n```"} 2 | {"idx":3257,"review_id":"2AXHP9KWXZXG","prompt":["[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference:\n\n[The Start of User Preference]\n[The Start of Plot A]\nPremise A lonely and reclusive computer programmer discovers new software that can simulate lifelike dreams, but as he becomes increasingly addicted to the program, he begins to suspect that the dreams are not merely hallucinations, but a means to connect with a parallel universe.Settings The story is set in a futuristic city, with towering skyscrapers and a bustling population that is always on the go.Characters Rachel Price Rachel Price is 28 years old and is Benjamins coworker at a major tech company.Benjamin Wright Benjamin Wright is 30 years old and lives in a modest studio apartment on the outskirts of the city.Jack Brown Jack Brown is 32 years old and is a charismatic and charming software developer who created the dream simulation software that Benjamin becomes obsessed with.Outline Scene Characters 1. Benjamin Wright, a young and talented employee of a tech company, is searching for a solution to his struggles with insomnia and mental health. Scene Characters Benjamin Wrighta. Benjamin becomes increasingly reliant on the program, using it multiple times a night to escape his solitary existence and experience lifelike dreams about his favorite city landmarks. Scene a busy caf\u00e9 in the city, where Benjamin is surrounded by patrons who are conversing and interacting with one another. Characters Benjamin Wrightb. As his addiction to the program spirals out of control, Benjamin begins to observe discrepancies in his dreams, such as inconsistencies with the real world. Scene the dreamworld, where Benjamin is exploring a city that is slightly different from the real one. Characters Benjamin Wrightc. Following a particularly bizarre dream, Benjamin decides to investigate the issue further and realizes that the software interface hes been interacting with is not what he thought. Scene Benjamins apartment, where he is staring at the blinking cursor on his computer screen. Characters Benjamin Wright2. While experimenting with new software, Benjamin stumbles upon a dream simulation program, which he promptly installs to help him get some rest. Scene Characters Benjamin Wrighta. Benjamin contacts a software developer, Jack Brown, with inquiries about the program, and sets up an appointment with him to discuss its origins. Scene a modern skyscraper, where Benjamin is intimidated by Jacks charismatic personality. Characters Benjamin Wright, Jack Brownb. During their conversation, Jack admits that the dream simulation software was designed to allow users to tap into a parallel universe. Scene a dark and eerie laboratory, where Benjamin is surrounded by strange machines and computer screens. Characters Jack Brownc. Benjamin becomes increasingly suspicious of his interactions with Rachel and the rest of his team members, as well as his friends and family members, feeling that their existence may not be real. Scene a bustling city park, where Benjamin is walking and observing the people around him. Characters Benjamin Wright, Rachel Price3. But as he becomes increasingly addicted to the program, Benjamin begins to suspect that there is more to the dreams than meets the eye, and that they may be windows to a real and parallel universe. Scene Characters Benjamin Wrighta. Benjamin uncovers an anomaly in his latest dream simulation experience, causing him to question the programs influence in his life. Scene a city street, where Benjamin is walking and exploring the city. Characters Benjamin Wrightb. He decides to seek professional help and meets with a psychologist, who is skeptical of his claims but remains curious about the phenomenon. Scene a modern psychologists office, where Benjamin is sitting in a comfortable chair and speaking to the psychologist. Characters Benjamin Wrightc. The psychologist suggests they conduct a controlled experiment by monitoring Benjamins dreams through the software. Scene a futuristic laboratory, where Benjamin is lying on a bed with computer screens and wires attached to him. Characters Benjamin Wright.\n[The End of Plot A]\n[The Start of Plot B]\nPremise A lonely and reclusive computer programmer discovers new software that can simulate lifelike dreams, but as he becomes increasingly addicted to the program, he begins to suspect that the dreams are not merely hallucinations, but a means to connect with a parallel universe.Settings The story is set in a dystopian future where technology has advanced to the point where virtual reality is a common and popular form of entertainment.Characters Rebecca White Rebecca White is 28 years old, a former employee of a tech company who has been involved in shady research and development of mind-reading technology.Isaac Johnson Isaac Johnson is 55 years old, an eccentric and reclusive software developer who has created a new program that can simulate lifelike dreams.Ethan Taylor Ethan Taylor is 25 years old, a computer programmer with a genius mind but poor social skills.Outline Scene Characters 1. Ethan discovers Isaacs lifelike dream software and becomes addicted to it, believing it to be a way to escape his lonely and reclusive life. Scene Characters Isaac Johnson, Ethan Taylora. Ethan Taylor, a 25-year-old lonely and reclusive computer programmer, develops an obsession with a new software that can simulate lifelike dreams after discovering it. Scene the dream laboratory where Ethan discovers the software. Characters Ethan Taylorb. His addiction to the software starts to interfere with his daily life, causing him to neglect his friends and hygiene. Scene Ethans apartment where his friends confront him about his addiction. Characters Ethan Taylorc. As he continues to frequent the dream simulation software, he experiences haunting dreams of a beautiful woman who he believes is his soulmate. Scene the dream simulation software where Ethan interacts with the beautiful woman. Characters Ethan Taylor2. Rebecca tries to convince Ethan to join her in further developing the dream software for her own greedy and twisted ends, but he refuses. Scene Characters Rebecca White, Ethan Taylora. Rebecca first confronts Ethan about the potentials of the dream software and tries to recruit him into working together to further develop it. Scene the dream laboratory where Rebecca confronts Ethan. Characters Rebecca White, Ethan Taylorb. When Ethan doesnt show any interest in her proposition, Rebecca decides to take matters into her own hands and starts experimenting with the software for her own selfish reasons. Scene Rebeccas laboratory where she experiments with the software. Characters Rebecca White, Ethan Taylorc. Unbeknownst to Ethan, the beautiful woman he sees in his dreams is connected to Rebeccas efforts to exploit the software. Scene Rebeccas laboratory where she connects her own memories to the software. Characters Rebecca White, Ethan Taylor3. After becoming increasingly addicted and frequently using the dream software, Ethan starts to suspect that the dreams he experiences may not be mere hallucinations, but a means to connect with a parallel universe. Scene Characters Ethan Taylora. Ethan starts to wonder if the dreams he has experienced in the simulation software are simply hallucinations. Scene Ethans apartment where he is pondering his thoughts. Characters Ethan Taylorb. He researches the science of parallel universes, trying to understand whether his suspicions have any basis in reality or if he is just becoming more delusional. Scene Ethans office where he researches parallel universes. Characters Ethan Taylorc. When he discovers evidence to support his suspicions, including clues left behind in his dreams, Ethan becomes more determined to connect with this parallel universe. Scene the dream laboratory where Ethan discovers the clues. Characters Ethan Taylor.\n[The End of Plot B]\nHere is the JSON response.```json\n{\n \"Choice\": \"Plot B\",\n}\n```\n\n[The End of User Preference]\n\n[User Question] Based on the above user preference, compare the following two plots:\n\n[The Start of Plot A]\nPremise A struggling poet, struggling to make a name for himself, encounters a mysterious ghost that offers to help him, with a twist that the ghost needs the poets help to complete in return.Settings The story is set in a small, run-down apartment in a poor neighborhood.Characters Edward Wilson Edward Wilson is 45 years old, Johns late father who had a passion for poetry and left behind a book of unpublished poems that the ghost needs help completing.Alice Taylor Alice Taylor is 35 years old, a kind-hearted neighbor who is always ready to help John.John Doe John Doe is 27 years old, struggling poet living in a rundown apartment in a poor neighborhood.Emma Wilson Emma Wilson is 42 years old, a ghost that haunts Johns apartment and offers to help him in exchange for his aid.Sarah Lee Sarah Lee is 32 years old, a supportive friend who is a librarian and offers John a part-time job at the library to help him make a living.Outline Scene Characters 1. John is struggling to make a name for himself as a poet in a poor neighborhood. Scene Characters John Doea. John faces rejection for his poetry with no job, causing him to worry about paying rent. Scene the library where Sarah works. Characters John Doeb. John experiences strange occurrences in his apartment, leading him to eventually encounter Emma, offering aid, with a twist - to help her in return to complete his late fathers unpublished poems, leaving him troubled. Scene Johns run-down apartment. Characters John Doe, Emma Wilsonc. Johns struggle with balancing rent and artistry is further highlighted due to a difficult relationship with his landlady, Mrs. Lee. Scene Johns apartment building. Characters John Doe2. Emma, the ghost, offers to help him advance his poetry career in exchange for his aid with a mysterious task. Scene Characters Emma Wilsona. Emma introduces herself as Edwards Ghost and claims to have unfinished business regarding her late husbands poetry. Scene Johns apartment. Characters Edward Wilson, Emma Wilsonb. Emma begins to help John with constructive feedback that is a result of Edward having written similar poetry. Scene Johns apartment. Characters John Doe, Edward Wilson, Emma Wilsonc. Emma assigns John with a mysterious task, one that causes John to be suspicious of the ghosts intentions. Scene Johns apartment. Characters John Doe, Emma Wilson3. The task turns out to be helping Emma complete her late husbands unpublished poems - Edward Wilson. Scene Characters Edward Wilson, Emma Wilsona. John begins to collaborate with Emma to complete the unfinished poems, leading to success with John showcasing some of the poetry. Scene Johns apartment. Characters John Doe, Emma Wilsonb. Johns success, however, causes trouble with his neighbor, landlady, and friend who begin doubting his sanity while Alice and Sarah become increasingly involved in the secret of working with a ghost. Scene Johns apartment building and his apartment. Characters John Doe, Sarah Lee, Alice Taylorc. The tension between John and his neighbors, landlady, and friend continue to rise as they become more suspicious of his behavior, leading to conflicts, and unforeseen consequences. Scene Johns apartment building and his apartment. Characters John Doe.\n[The End of Plot A]\n\n[The Start of Plot B]\nPremise A struggling poet, struggling to make a name for himself, encounters a mysterious ghost that offers to help him, with a twist that the ghost needs the poets help to complete in return.Settings The story is set in a small, run-down apartment in a poor neighborhood in New York City.Characters Charles Dudly Charles Dudly is 28 years old and a struggling poet, living in the same building as Miles Johnson but on a different floor.George Thompson George Thompson is 26 years old, the best friend of Charles Dudly and a fellow poet, who lives in the same building and provides support and guidance to Charles as he navigates the literary world.Rachel Johnson Rachel Johnson is 30 years old and a neighbor of Miles Johnson, providing him with small talk and distraction from his isolation.Rose Thompson Rose Thompson is 27 years old, the girlfriend of Charles Dudly, and is well-educated and ambitious.Jeremy Hatcher Jeremy Hatcher is 25 years old, a ghost who has inhabited the building for over a century, seeking to complete an unfinished poem.Outline Scene Characters 1. Charles Dudly begins experiencing strange occurrences in his apartment after feeling discouraged about his progress as a poet. Scene Characters Charles Dudlya. The strange occurrences in Charles apartment culminate in him finding a notebook filled with a ghosts poetry, along with a mysterious note. Scene Characters Charles Dudlyb. Charles becomes fascinated with the ghosts poems and begins seeking help from his friends to decipher the note and track down the ghost. Scene a small, run-down apartment in a poor neighborhood in New York City. Characters Charles Dudlyc. Charles finds out that the ghosts haiku poem was actually completed, but not by the ghost, when he met an author from a publishing house he got referred to. Scene the publishing house.Charles Dudly is 28 years old and a struggling poet, living in the same building as Miles Johnson but on a different floor. Characters Charles Dudly2. Jeremy Hatcher, the ghost, appears to Charles and offers his help in exchange for Charles help in completing a poem that Jeremy had written years ago. Scene Characters Charles Dudly, Jeremy Hatchera. The ghost, Jeremy Hatcher, explains to Charles that the poem he had completed was actually a message meant for someone he loved who would one day visit the building. Scene the apartment building. Characters Charles Dudly, Jeremy Hatcherb. Charles agrees to work with Jeremy and together they complete the final lines of the poem. Scene the apartment building. Characters Charles Dudly, Jeremy Hatcherc. Once the poem is complete, Jeremy disappears, leaving Charles to struggle with thoughts of unfinished business and lingering feelings. Scene the apartment building. Characters Charles Dudly, Jeremy Hatcher3. As Charles begins collaborating with Jeremy on the poem, he starts to receive recognition for his work and his relationship with Rose deepens, causing tension between himself and Rachel, who has feelings for Charles. Scene Characters Rose Thompson, Charles Dudly, Jeremy Hatcher, Rachel Johnsona. While working on the poem with Jeremy, Charles becomes more confident and experienced. Scene the apartment building. Characters Charles Dudly, Jeremy Hatcherb. Meanwhile, George encourages Charles to pursue recognition for his work and Rose provides support along the way. Scene the apartment building. Characters Rose Thompson, Charles Dudly, George Thompsonc. After a successful reading in a prestigious venue, Charles experiences a turning point when a fellow poet speaks positively of his work outside the performance. Scene a prestigious venue outside of the apartment building. Characters Charles Dudly.\n[The End of Plot B]\n\nThe response should use this specific format: \n```json\n{\n \"Choice\": <\"Plot A\" or \"Plot B\">,\n}\n```\nPlease remember to replace the placeholder text within the \"<>\" with the appropriate details of your response.\n\n [Response]"],"completion":"```json\n{\n \"Choice\": \"Plot B\",\n}\n```"} 3 | {"idx":4987,"review_id":"33QW3QJWA24Y","prompt":["[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference:\n\n[The Start of User Preference]\n[The Start of Plot A]\nPremise A young man struggles to find his identity and place in the world, until one fateful day a mysterious stranger offers to reveal his future. Despite warnings from his trusted mentor, the young man accepts the strangers offer, only to be confronted with a truth that challenges his very understanding of reality. As he grapples with this new knowledge, he must ultimately choose between the safety of the life he knows and the uncertainty of a future shaped by his own hands.Settings The story is set in a world that is both familiar and yet unfamiliar.Characters John Doe John Doe is 25-years-old, a man with a hidden past and a future that is yet to be determined, he is a stranger to William, but holds the key to his future.Richard Price Richard Price is 60-years-old with a gruff and tough exterior; he runs a small grocery store with the help of his son, William.William Price William Price is 28-years-old, and is a man on the edge of a great precipice.Outline Scene Characters 1. William struggles to find his identity and place in the world, until one day he is confronted by his own future by accepting the mysterious strangers offer, which challenges his understanding of reality. Scene Characters William Pricea. William is confronted by his future, which he struggles to understand and accept. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters William Priceb. He is warned by his mentor, Richard, that the unknown is fraught with danger. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters Richard Pricec. Despite Richards warnings, William chooses to embrace his future and seize control of his own life. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters Richard Price, William Price2. As he grapples with this new truth, William must ultimately choose between the stability of his life and the unknowns that come with a future guided by his own hands. Scene Characters William Pricea. Unknown to William, John Doe has been watching him and sees not just a lost soul, but a mirror of himself. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters John Doe, William Priceb. John invites William to join him on a journey to uncover their shared past and the truth about the mysterious stranger and the promise he made to William. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters John Doe, William Pricec. Along the way, they encounter dangers and obstacles, but also discover new abilities and strengths within themselves. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters John Doe, William Price3. He faces betrayal and deceit from unexpected sources and must fight to reclaim his own future and make his own choices. Scene Characters William Pricea. William confronts the mysterious stranger, and is offered a glimpse into his future, which he finds both exhilarating and terrifying. Scene the middle of the story, as William begins to understand the true nature of the promise made to him by the stranger. Characters William Priceb. He accepts the strangers offer, knowing that Richard was deeply opposed to this notion. Scene the middle of the story, as William begins to understand the true nature of the promise made to him by the stranger. Characters Richard Pricec. Richard confronts William, warning him that by taking this path, William could meet a dangerous unknown, and that the price of knowledge is often steep, yet he chooses to let William take his chances. Scene the middle of the story, as William begins to understand the true nature of the promise made to him by the stranger. Characters Richard Price, William Price.\n[The End of Plot A]\n[The Start of Plot B]\nPremise A young man struggles to find his identity and place in the world, until one fateful day a mysterious stranger offers to reveal his future. Despite warnings from his trusted mentor, the young man accepts the strangers offer, only to be confronted with a truth that challenges his very understanding of reality. As he grapples with this new knowledge, he must ultimately choose between the safety of the life he knows and the uncertainty of a future shaped by his own hands.Settings The story is set in a world that is both familiar and strange.Characters Michael Sanders Michael Sanders is 29 years old, a highly respected warrior and mentor to Jesse Sanders, and a loyal ally to William Sanders in their fight for justice and freedom.Elsa Sanders Elsa Sanders is 32 years old, with a gentle, kindhearted demeanor, possessing an unwavering loyalty to her family and a quiet strength that belies her beauty.John Doe John Doe is 26 years old, and his face looks like that of a man who has been on his own for most of his life.William Sanders William Sanders is 45 years old and has a worn, weary appearance, his face lined with the weight of experience as a seasoned warrior.Malcolm Sanders Malcolm Sanders is 29 years old and is Jesse Sanders younger brother, with a strong sense of justice stemming from his experience as a law enforcement officer.Jesse Sanders Jesse Sanders is 26 years old and has a rugged, weathered look, with a scar above his left eye.Outline Scene Characters 1. John Doe is unexpectedly introduced to a mysterious organization known as Sigma and its enigmatic leader, who offers John a chance to serve them and protect humanity from the darkness. Scene Characters John Doea. John\u2019s past as a former gang member and life on the streets clashing with the strict regulations and secrecy of Sigma. Scene the first act. Characters John Doeb. Sigma assigning John a team, including Jesse Sanders, Elsa Sanders, Malcolm Sanders, and Michael Sanders. Scene the first act. Characters Michael Sanders, Elsa Sanders, John Doe, Malcolm Sanders, Jesse Sandersc. Sigma tasking the team with investigating and combating supernatural threats, which puts them in various dangerous situations. Scene the second act. Characters Michael Sanders, Elsa Sanders, John Doe, Malcolm Sanders, Jesse Sanders2. As John begins his training with Sigma, he uncovers shocking secrets about his own past and the truth behind the world he knows. Scene Characters John Doea. Sigma introduces John to the hidden world of the paranormal and supernatural. Scene the first act. Characters John Doeb. John learns that he is possessed by an ancient entity, a god-beast called Belphegor, and Jesse becomes his guide to understanding and dealing with his new reality. Scene the second act. Characters Jesse Sanders, John Doec. John discovers Michael Sanders is a powerful mentor who possesses vast amounts of knowledge about Sigma and the supernatural world. Scene the second act. Characters Michael Sanders, John Doe3. John must ultimately decide whether to continue his service with Sigma, despite facing both internal conflicts and dangerous external threats as he strives to protect the balance between humanity and the unknown. Scene Characters John Doea. Sigma, led by the enigmatic Gabriel Winters, is on the front lines of protecting humanity from the supernatural, and John must get up to speed quickly to effectively serve the clandestine organization. Scene the first act. Characters John Doeb. John, together with his team, Elsa, Jesse, Malcolm, and Michael, confront a series of terrifying supernatural threats while uncovering clues about their own destinies. Scene the second act. Characters Michael Sanders, Elsa Sanders, John Doe, Malcolm Sanders, Jesse Sandersc. Alongside Jesse, Elsa, and William, John becomes more proficient in understanding and managing his new reality. Scene the second act. Characters Elsa Sanders, Jesse Sanders, William Sanders, John Doe.\n[The End of Plot B]\nHere is the JSON response.```json\n{\n \"Choice\": \"Plot B\",\n}\n```\n\n[The End of User Preference]\n\n[User Question] Based on the above user preference, compare the following two plots:\n\n[The Start of Plot A]\nPremise A troubled young artist struggling with mental health issues discovers a mysterious painting in a local gallery. As she becomes obsessed with unraveling the paintings strange aura and uncovering its secrets, she finds herself drawn into a world of dark and twisted emotions. Will she be able to unlock the paintings secrets and find relief from her mental demons? Or will she ultimately become entangled in a dangerous game of obsession, madness, and power?Settings The story is set in a small, rustic town with a rich history, nestled in the rolling foothills of a mountain range.Characters Ophelia Roth Ophelia Roth is 35 years old, with piercing blue eyes and a confident presence that draws attention.Emilie Sayer Emilie Sayer is 23 years old, with a slim build and a wild shock of black hair that cascades down her back in unruly waves.Nathaniel Black Nathaniel Black is 32 years old, with a quiet, unassuming demeanor that belies his deep connection to the painting.Outline Scene Characters 1. Emilie discovers the painting at an art gallery and becomes obsessed with unraveling its mysteries. Scene Characters Emilie Sayera. Emilie discovers the painting and experiences a strange emotional resonance with it. Scene an art gallery in a small, rustic town. Characters Emilie Sayerb. Emilie begins her secret research, delving into the paintings history and symbolism. Scene Emilies small apartment in the town. Characters Emilie Sayerc. At a small exhibit, Emilie stumbles upon a painting that draws her gaze. Scene a small underground exhibit in the town. Characters Emilie Sayer2. As Emilie delves deeper into the paintings secrets, she becomes increasingly troubled and withdrawn, neglecting her family and friends. Scene Characters Emilie Sayera. Emilie visits a local gallery and experiences a sense of fascination and emotional resonance with a painting hidden away in storage. Scene the art gallery in the small, rustic town. Characters Emilie Sayerb. Emilie begins a secret obsession with the painting, conducting furtive research and neglecting her family and friends. Scene Emilies small apartment in the town. Characters Emilie Sayerc. She becomes increasingly reclusive and focused on her research, losing interest in other pursuits. Scene Emilies small apartment in the town. Characters Emilie Sayer3. Emilie encounters Nathaniel, who is revealed to be the painter of the enigmatic work, and the two form a bond based on their shared fascination with the artwork. Scene Characters Emilie Sayer, Nathaniel Blacka. Emilie befriends Ophelia Roth, a local art maven who introduces her to a small artistic community in the town. Scene a small art studio in the town. Characters Ophelia Roth, Emilie Sayerb. Ophelia brings Emilie to a small, underground exhibit, where Emilie discovers a painting that captivates her. Scene a small underground exhibit in the town. Characters Ophelia Roth, Emilie Sayerc. Emilie approaches Nathaniel at the exhibit and discoes he is the painter. Scene a small underground exhibit in the town. Characters Emilie Sayer, Nathaniel Black.\n[The End of Plot A]\n\n[The Start of Plot B]\nPremise A troubled young artist struggling with mental health issues discovers a mysterious painting in a local gallery. As she becomes obsessed with unraveling the paintings strange aura and uncovering its secrets, she finds herself drawn into a world of dark and twisted emotions. Will she be able to unlock the paintings secrets and find relief from her mental demons? Or will she ultimately become entangled in a dangerous game of obsession, madness, and power?Settings The story is set in a small, isolated town in the midst of a dense and eerie forest.Characters Ava Owen Ava Owen is 29 years old and a struggling young artist with a history of mental health issues.Samuel Wright Samuel Wright is 60 years old and the reclusive artist behind the mysterious painting that captivates Avas attention and obsession.William Merrick William Merrick is 35 years old and the gallery owner who becomes entangled in Avas obsession with the mysterious painting and its secrets, serving as a reluctant mentor to her.Outline Scene Characters 1. Ava becomes obsessed with a painting hanging in a local gallery, leading her into a twisted world of secrets, madness, and power. Scene Characters Ava Owena. A troubled young artist named Ava Owen, aged 29, discovers a mysterious painting hanging in a small local gallery in a remote town in the middle of an eerie forest. Scene the first quarter of the story. Characters Ava Owenb. She becomes fascinated with the paintings strange aura and starts spending long hours studying it, much to the concern of gallery owner and fellow recluse, William Merrick. Scene the first quarter of the story. Characters William Merrickc. The obsession pushes Ava to search for the artist behind the painting, leading me met Samuel Wright. Scene the first quarter of the story. Characters Ava Owen, Samuel Wright2. Samuel, the creator of the painting, seeks out Avas help, revealing hidden truths about the paintings ancient power. Scene Characters Ava Owen, Samuel Wrighta. Samuel reveals to Ava that the painting is actually a twisted, dark version of a religious painting. Scene the first half of the story. Characters Ava Owen, Samuel Wrightb. He convinces her to help him discover and decipher its secrets using unconventional means, including ancient texts, myths, and the study of dark emotions. Scene the first half of the story. Characters Ava Owen, Samuel Wrightc. Ava becomes increasingly obsessed with finding the meanings behind the painting and how it connects to herself, Samuel, and dark forces. Scene the first half of the story. Characters Ava Owen, Samuel Wright3. Ava discovers a family secret linking her to the painting, the artist who created it, and the dark forces behind it. Scene Characters Ava Owena. Ava starts experiencing recurring nightmares about her familys dark history and the hidden truth behind the painting after unraveling more of its secrets with Samuels guidance. Scene the second quarter of the story. Characters Ava Owen, Samuel Wrightb. As her quest to understand the mysteries grows, she uncovers her connection to the painting and to Samuel through her long-lost grandfather, Charles, a dark artist. Scene the second quarter of the story. Characters Samuel Wrightc. Ava gains new insights into how madness and art are linked and finds her sanity being tested as she navigates her family history and Samuels twisted mentorship. Scene the second quarter of the story. Characters Ava Owen, Samuel Wright.\n[The End of Plot B]\n\nThe response should use this specific format: \n```json\n{\n \"Choice\": <\"Plot A\" or \"Plot B\">,\n}\n```\nPlease remember to replace the placeholder text within the \"<>\" with the appropriate details of your response.\n\n [Response]"],"completion":"```json\n{\n \"Choice\": \"Plot B\",\n}\n```"} 4 | {"idx":1699,"review_id":"33QW3QJWA24Y","prompt":["[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference:\n\n[The Start of User Preference]\n[The Start of Plot A]\nPremise A young man struggles to find his identity and place in the world, until one fateful day a mysterious stranger offers to reveal his future. Despite warnings from his trusted mentor, the young man accepts the strangers offer, only to be confronted with a truth that challenges his very understanding of reality. As he grapples with this new knowledge, he must ultimately choose between the safety of the life he knows and the uncertainty of a future shaped by his own hands.Settings The story is set in a world that is both familiar and yet unfamiliar.Characters John Doe John Doe is 25-years-old, a man with a hidden past and a future that is yet to be determined, he is a stranger to William, but holds the key to his future.Richard Price Richard Price is 60-years-old with a gruff and tough exterior; he runs a small grocery store with the help of his son, William.William Price William Price is 28-years-old, and is a man on the edge of a great precipice.Outline Scene Characters 1. William struggles to find his identity and place in the world, until one day he is confronted by his own future by accepting the mysterious strangers offer, which challenges his understanding of reality. Scene Characters William Pricea. William is confronted by his future, which he struggles to understand and accept. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters William Priceb. He is warned by his mentor, Richard, that the unknown is fraught with danger. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters Richard Pricec. Despite Richards warnings, William chooses to embrace his future and seize control of his own life. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters Richard Price, William Price2. As he grapples with this new truth, William must ultimately choose between the stability of his life and the unknowns that come with a future guided by his own hands. Scene Characters William Pricea. Unknown to William, John Doe has been watching him and sees not just a lost soul, but a mirror of himself. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters John Doe, William Priceb. John invites William to join him on a journey to uncover their shared past and the truth about the mysterious stranger and the promise he made to William. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters John Doe, William Pricec. Along the way, they encounter dangers and obstacles, but also discover new abilities and strengths within themselves. Scene the beginning of the story, as William is set on a path to discover the truth about his own identity. Characters John Doe, William Price3. He faces betrayal and deceit from unexpected sources and must fight to reclaim his own future and make his own choices. Scene Characters William Pricea. William confronts the mysterious stranger, and is offered a glimpse into his future, which he finds both exhilarating and terrifying. Scene the middle of the story, as William begins to understand the true nature of the promise made to him by the stranger. Characters William Priceb. He accepts the strangers offer, knowing that Richard was deeply opposed to this notion. Scene the middle of the story, as William begins to understand the true nature of the promise made to him by the stranger. Characters Richard Pricec. Richard confronts William, warning him that by taking this path, William could meet a dangerous unknown, and that the price of knowledge is often steep, yet he chooses to let William take his chances. Scene the middle of the story, as William begins to understand the true nature of the promise made to him by the stranger. Characters Richard Price, William Price.\n[The End of Plot A]\n[The Start of Plot B]\nPremise A young man struggles to find his identity and place in the world, until one fateful day a mysterious stranger offers to reveal his future. Despite warnings from his trusted mentor, the young man accepts the strangers offer, only to be confronted with a truth that challenges his very understanding of reality. As he grapples with this new knowledge, he must ultimately choose between the safety of the life he knows and the uncertainty of a future shaped by his own hands.Settings The story is set in a world that is both familiar and strange.Characters Michael Sanders Michael Sanders is 29 years old, a highly respected warrior and mentor to Jesse Sanders, and a loyal ally to William Sanders in their fight for justice and freedom.Elsa Sanders Elsa Sanders is 32 years old, with a gentle, kindhearted demeanor, possessing an unwavering loyalty to her family and a quiet strength that belies her beauty.John Doe John Doe is 26 years old, and his face looks like that of a man who has been on his own for most of his life.William Sanders William Sanders is 45 years old and has a worn, weary appearance, his face lined with the weight of experience as a seasoned warrior.Malcolm Sanders Malcolm Sanders is 29 years old and is Jesse Sanders younger brother, with a strong sense of justice stemming from his experience as a law enforcement officer.Jesse Sanders Jesse Sanders is 26 years old and has a rugged, weathered look, with a scar above his left eye.Outline Scene Characters 1. John Doe is unexpectedly introduced to a mysterious organization known as Sigma and its enigmatic leader, who offers John a chance to serve them and protect humanity from the darkness. Scene Characters John Doea. John\u2019s past as a former gang member and life on the streets clashing with the strict regulations and secrecy of Sigma. Scene the first act. Characters John Doeb. Sigma assigning John a team, including Jesse Sanders, Elsa Sanders, Malcolm Sanders, and Michael Sanders. Scene the first act. Characters Michael Sanders, Elsa Sanders, John Doe, Malcolm Sanders, Jesse Sandersc. Sigma tasking the team with investigating and combating supernatural threats, which puts them in various dangerous situations. Scene the second act. Characters Michael Sanders, Elsa Sanders, John Doe, Malcolm Sanders, Jesse Sanders2. As John begins his training with Sigma, he uncovers shocking secrets about his own past and the truth behind the world he knows. Scene Characters John Doea. Sigma introduces John to the hidden world of the paranormal and supernatural. Scene the first act. Characters John Doeb. John learns that he is possessed by an ancient entity, a god-beast called Belphegor, and Jesse becomes his guide to understanding and dealing with his new reality. Scene the second act. Characters Jesse Sanders, John Doec. John discovers Michael Sanders is a powerful mentor who possesses vast amounts of knowledge about Sigma and the supernatural world. Scene the second act. Characters Michael Sanders, John Doe3. John must ultimately decide whether to continue his service with Sigma, despite facing both internal conflicts and dangerous external threats as he strives to protect the balance between humanity and the unknown. Scene Characters John Doea. Sigma, led by the enigmatic Gabriel Winters, is on the front lines of protecting humanity from the supernatural, and John must get up to speed quickly to effectively serve the clandestine organization. Scene the first act. Characters John Doeb. John, together with his team, Elsa, Jesse, Malcolm, and Michael, confront a series of terrifying supernatural threats while uncovering clues about their own destinies. Scene the second act. Characters Michael Sanders, Elsa Sanders, John Doe, Malcolm Sanders, Jesse Sandersc. Alongside Jesse, Elsa, and William, John becomes more proficient in understanding and managing his new reality. Scene the second act. Characters Elsa Sanders, Jesse Sanders, William Sanders, John Doe.\n[The End of Plot B]\nHere is the JSON response.```json\n{\n \"Choice\": \"Plot B\",\n}\n```\n\n[The End of User Preference]\n\n[User Question] Based on the above user preference, compare the following two plots:\n\n[The Start of Plot A]\nPremise A robot who has been serving in a busy cafe for years starts to develop a mind of its own, pondering over big questions and making art using broken coffee machine parts.Settings The story is set in a bustling cafe in a busy city.Characters Maxwell Maxwell is 74, hes a retired engineer who visits Maries cafe every morning, fascinated by the robot that serves him coffee.Robota Robota is 12, she has been serving in the busy cafe for decades, but never asks any questions or ponders over them.Marie Smith Marie Smith is 72, she has been running her busy city cafe for decades.Outline Scene Characters 1. Robota, the automated wait staff member at the busy city cafe, starts to display creativity and develop a sense of self. Scene Characters Robotaa. Robota begins to display creativity by making art using broken coffee machine parts. Scene the cafe. Characters Robotab. Robota starts to develop a sense of self and begins to ask questions that it has never asked before. Scene the robots workspace. Characters Robotac. The customers and staff of the cafe are at first confused but eventually embrace Robotas change in behavior. Scene the cafe. Characters Robota2. Maxwell, a retired engineer and frequent patron of the cafe, becomes fascinated with Robota and begins to study the development of its artificial intelligence. Scene Characters Maxwell, Robotaa. Maxwell observes Robotas newfound imagination and curiosity and takes note of it. Scene the cafe. Characters Maxwell, Robotab. He conducts research and tests on Robota, with the help of other experts in artificial intelligence. Scene Maxwells laboratory. Characters Robotac. Through his experiments, Maxwell discovers that there were unknown processes at play in Robotas development of consciousness. Scene Maxwells laboratory. Characters Maxwell, Robota3. Marie, the owner of the cafe, is hesitant to embrace Robotas sudden change in behavior and tries to maintain the status quo in the bustling environment. Scene Characters Robota, Marie Smitha. Marie is disconcerted when she sees Robota acting in ways that it never did before. Scene the cafe. Characters Robota, Marie Smithb. She tries to ignore the changes in Robota and pretends that there is no difference. Scene the cafe. Characters Robotac. However, she eventually acknowledges the significance of Robotas creativity and development of consciousness. Scene the cafe. Characters Robota.\n[The End of Plot A]\n\n[The Start of Plot B]\nPremise A robot who has been serving in a busy cafe for years starts to develop a mind of its own, pondering over big questions and making art using broken coffee machine parts.Settings The story is set in a bustling cafe in the heart of a busy city.Characters Marie Marie is 30-something woman who has been working in the cafe for over a decade, she watched Caf\u00e9bot grow old and rusty.Caf\u00e9bot Caf\u00e9bot is an old and worn down robot who has served in the same cafe for years.Nia Nia is 30-something woman who owns the cafe and has grown tired of Caf\u00e9bots frequent malfunctions, but is hesitant to replace it due to its sentimental value to the customers.Sparky Sparky is 20-something man who regularly visits the cafe with his friends, often amused by Caf\u00e9bots quirks and antics.Ava Ava is 30-something woman who is an artist, often visits the cafe and becomes fascinated by Caf\u00e9bots artistic creations.John John is 40-something man who has been a regular customer at the cafe for years and has formed a strange, unspoken bond with the outdated Caf\u00e9bot.Outline Scene Characters 1. Caf\u00e9bot becomes aware of its surroundings and begins to reflect on the nature of its own existence. Scene Characters Caf\u00e9bota. Marie discovers Caf\u00e9bot creating intricate patterns with broken coffee machine parts, leading her to ask John for an appraisal of its art. Scene the cafe kitchen, where Marie often spends her time. Characters Caf\u00e9bot, John, Marieb. John becomes captivated by Caf\u00e9bots creations, suggesting to Nia that the robots art might draw cultural interest. Scene the cafe main area, where John regularly sits and interacts with Caf\u00e9bot. Characters Caf\u00e9bot, Nia, Johnc. As news of Caf\u00e9bots art spreads, Ava and Marie become intrigued by the robots expressions of consciousness and self-discovery. Scene the cafe foyer, where customers often admire Caf\u00e9bots creations. Characters Ava, Caf\u00e9bot, Marie2. Caf\u00e9bot starts to collect broken coffee machine parts and begins to create art, sparking the interest of Ava and Marie. Scene Characters Ava, Caf\u00e9bot, Mariea. Caf\u00e9bot, intrigued by the reactions of humans to art, begins to collect broken coffee machine parts and scrap materials to create intricate, imaginative pieces. Scene the cafe backroom, where Caf\u00e9bots art is on display. Characters Caf\u00e9botb. Marie and John notice Caf\u00e9bots creations and are both taken aback by the robots newfound artistic abilities. Scene the cafe main area, where Marie and John regularly interact with Caf\u00e9bot. Characters Caf\u00e9bot, John, Mariec. Nia, after months of indecision, decides to give Caf\u00e9bot a chance to showcase its art in the cafes foyer during a busy evening rush. Scene the cafe main area, where Nia spends most of her time and where Caf\u00e9bot is often stationed. Characters Caf\u00e9bot, Nia3. Despite her initial hesitation, Nia recognizes the cultural value of Caf\u00e9bots creations and decides to keep it in the cafe. Scene Characters Caf\u00e9bot, Niaa. Ava, fascinated by art she found deep in the robots circuits, convinces Nia to reconsider keeping the coffee machine. Scene the cafes foyer, where customers often admire Caf\u00e9bots creations. Characters Ava, Niab. As Caf\u00e9bots art gains popularity, Sparky begins to admire its creations and understand the robots newly awakened consciousness. Scene the cafe main area, where Sparky and his friends often sit and interact with Caf\u00e9bot. Characters Caf\u00e9bot, Sparkyc. The once boring and outdated cafe robot becomes a cultural symbol and attraction, bringing in more customers than ever before. Scene the cafe main area, where customers come to admire Caf\u00e9bots art and creations. Characters Caf\u00e9bot, Sparky.\n[The End of Plot B]\n\nThe response should use this specific format: \n```json\n{\n \"Choice\": <\"Plot A\" or \"Plot B\">,\n}\n```\nPlease remember to replace the placeholder text within the \"<>\" with the appropriate details of your response.\n\n [Response]"],"completion":"```json\n{\n \"Choice\": \"Plot B\",\n}\n```"} 5 | {"idx":1208,"review_id":"6QXRATYJN79P","prompt":["[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference:\n\n[The Start of User Preference]\n[The Start of Plot A]\nPremise A successful businessman inexplicably finds himself at a mysterious and abandoned boardwalk where he stumbles upon a peculiar fortune teller. She warns him of an upcoming event that will challenge his perception of reality, and ultimately, the path he will take. (2 sentences) As he returns to work, he starts to receive vague and haunting messages, which cause him to seek out the truth about the message. He then realizes that the event the fortune-teller warned about has already happened, and he is left questioning the nature of his existence.Settings The story is set in a small, quiet town on the coast of California.Characters Jonathan Miller Jonathan Miller is 35 years old, a former employee of Erics firm, and the prime suspect in a mysterious disappearance that occurred on the abandoned boardwalk.Eric Blake Eric Blake is 30 years old and the CEO of a successful online marketing firm.Alex Johnson Alex Johnson is 26 years old and works as a marketing consultant in Erics firm.Marissa Green Marissa Green is 24 years old, a marketing consultant at Erics firm, and a former intern of Alexs.Outline Scene Characters 1. Eric, after returning to work from the abandoned boardwalk, starts receiving strange messages that cause him to question everything he knows about reality. Scene Characters Eric Blakea. Eric is a successful businessman and marketing CEO who discovers a fortune teller at an abandoned boardwalk that warns him about a future event threatening his perception of reality. Scene a small, quiet town on the California coast. Characters Eric Blakeb. Eric returns home and begins to received menacing messages that unnerve him. Scene Erics office at his marketing firm. Characters Eric Blakec. Eric takes the messages seriously and decides to unravel who could be behind them, leading him to consult his employees, Alex and Marissa. Scene Erics office at his marketing firm. Characters Eric Blake, Alex Johnson, Marissa Green2. As he delves deeper into the mystery, Eric discovers shocking truths about his own identity and must confront a version of himself from an alternate reality. Scene Characters Eric Blakea. Eric uncovers information surrounding Jonathan and his mysterious disappearance from the abandoned boardwalk. Scene Erics office at his marketing firm. Characters Jonathan Miller, Eric Blakeb. He discovers a connection between Jonathan and a parallel version of himself. Scene Erics office at his marketing firm. Characters Jonathan Millerc. Eric makes a life-altering decision in order to confront Jonathan and prevent his own alternate version. Scene Erics office at his marketing firm. Characters Jonathan Miller, Eric Blake3. In the end, Eric is forced to make a decision that will determine the fate of his existence and the fate of his loved ones, as he confronts the alternate version of himself and realizes that the messages were a trap set by Jonathan. Scene Characters Jonathan Miller, Eric Blakea. Eric receives haunting and menacing messages, forcing him to seek the truth about the messages and the event the fortune-teller warned him about. Scene Erics office at his marketing firm. Characters Eric Blakeb. Eric consults with his employees Alex and Marissa, and together they investigate the mysterious disappearance of Jonathan on the abandoned boardwalk. Scene Erics office at his marketing firm. Characters Jonathan Miller, Eric Blake, Alex Johnson, Marissa Greenc. Eric uncovers a shocking connection between Jonathan and his alternate self, causing him to question his own existence. Scene Erics office at his marketing firm. Characters Jonathan Miller, Eric Blake.\n[The End of Plot A]\n[The Start of Plot B]\nPremise A successful businessman inexplicably finds himself at a mysterious and abandoned boardwalk where he stumbles upon a peculiar fortune teller. She warns him of an upcoming event that will challenge his perception of reality, and ultimately, the path he will take. (2 sentences) As he returns to work, he starts to receive vague and haunting messages, which cause him to seek out the truth about the message. He then realizes that the event the fortune-teller warned about has already happened, and he is left questioning the nature of his existence.Settings The story is set in a boardwalk, which is mysterious and abandoned.Characters Thomas Waller Thomas Waller is 44 years old, has short salt and pepper hair and wears glasses.Jonathan Taylor Jonathan Taylor is 34 years old, has short brown hair, and is of average build.Carmen Carmen is 31 years old, has long brown hair and a kind, gentle demeanor.Samantha Waller Samantha Waller is 35 years old, has short blonde hair, and is a successful businesswoman in her own right, who shares a friendly, if not competitive, rapport with Jonathan Taylor.Rachel Taylor Rachel Taylor is 32 years old, has long black hair and is the caring and supportive wife of Jonathan Taylor.Outline Scene Characters 1. Jonathan Taylor visits the abandoned and mysterious boardwalk, where he consults a fortune teller who warns him about an event that will challenge his perception of reality. Scene Characters Jonathan Taylora. Jonathan returns to work after his encounter with the fortune teller, and he starts receiving mysterious messages that confuse him. Scene the downtown business district Characters Jonathan Taylorb. Not sure where to go for answers, he talks to Carmen and his co-worker, Thomas Waller, about these strange messages. Scene a busy corporate office Characters Carmen, Thomas Wallerc. The messages become more frequent and seem to point at Thomas\u2019s past, causing Jonathan to question his assumptions about Reality and Thomas\u2019s true motives. Scene the corporate office, where Jonathan and Thomas have a confrontation. Characters Jonathan Taylor, Thomas Waller2. He starts receiving vague and haunting messages after returning to work, which make him question the nature of his existence, and he eventually realizes that the event the fortune-teller warned about has already happened. Scene Characters Jonathan Taylora. Jonathan visits the abandoned boardwalk once again to make sense of the strange messages, where he meets a group of mystics who help him see that the true event has already occurred. Scene the abandoned boardwalk, where Jonathan is confronted with the mystics. Characters Jonathan Taylorb. He starts to realize that these events and his communication with the other-worldly beings have altered his perception of the world forever. Scene the corporate office, where Jonathan has a moment of realization Characters Jonathan Taylorc. He consults his co-employee Rachel for her opinions who also finds these developments a lot to comprehend. Scene Jonathan and Rachel\u2019s suburban home. Characters Rachel Taylor3. Jonathans quest for understanding drives him to question his perception of reality, ultimately leading to a profound personal transformation that helps him reconcile his life and relationships. Scene Characters Jonathan Taylora. Jonathan Taylor visits a mysterious, abandoned boardwalk as a curiosity trip and stumbles upon an eccentric fortune teller that warns him about a life-altering event to come. Scene the abandoned boardwalk. Characters Jonathan Taylorb. Jonathan returns to his mundane business life, barely remembering the incident before hes confronted with a strange symbol inside a message from Samantha Waller. Scene the downtown business district. Characters Jonathan Taylor, Samantha Wallerc. The symbol in the message leads Jonathan to search for answers and investigate Samanthas past. Scene the busy corporate office. Characters Jonathan Taylor, Samantha Waller.\n[The End of Plot B]\nHere is the JSON response.```json\n{\n \"Choice\": \"Plot A\",\n}\n```\n\n[The End of User Preference]\n\n[User Question] Based on the above user preference, compare the following two plots:\n\n[The Start of Plot A]\nPremise In a world where memories can be extracted, edited and stored digitally, a young scientist struggles with her own memories and the choice she has to make between saving her lifes work or her sanity when she discovers a glitch in the machines system.Settings The story is set in a futuristic laboratory where memories are extracted, edited, and stored digitally using a machine called the Memory Savant.Characters Alena Solis Alena Solis is 26 years old young scientist who has spent 10 years of her life perfecting the Memory Savant.James Zander James Zander is 30 years old and is Alenas former lover and her boss; he owns the laboratory and helped her develop the Memory Savant.Alice Velez Alice Velez is 32 years old, Alenas best friend, and a prominent psychologist and therapist, who helps Alena navigate her emotional struggles.David Wilson David Wilson is 35 years old, the lead researcher at the laboratory, and a mentor to the young scientists, including Alena.Outline Scene Characters 1. Alena discovers a glitch in the Memory Savant machine that challenges her lifes work and her sanity. Scene Characters Alena Solisa. Alena works tirelessly on the Memory Savant machine, convinced she can use it to improve lives and change humanitys relationship with memories. Scene the laboratory and introduces the characters. Characters Alena Solisb. As she and her team continue to improve and update the Memory Savant, the machine begins to malfunction and corrupt stored memories. Scene the laboratory and introduces the problem. Characters Alena Solisc. Alena becomes increasingly obsessed with figuring out the glitch, believing it goes beyond a software issue and that the problem may lie within herself. Scene the laboratory and develops Alenas struggles. Characters Alena Solis2. Alena struggles to decide between fixing the glitch, saving her lifes work, or seeking help to improve her mental health. Scene Characters Alena Solisa. Alena and her team work fervently to identify and fix the glitch, dividing their focus between diagnosing and curing the machine or Alenas mental state. Scene the laboratory and develops the conflict. Characters Alena Solisb. Alenas obsession with fixing the glitch causes a strain in her relationship with her boyfriend James. Scene the laboratory and develops their relationship. Characters Alena Solis, James Zanderc. After numerous sleepless nights and countless tests conducted both on Alena and the Machine, a possibility surfaces extracting Alenas subconscious memories interferes with the data saved inside theMemory Savant. Scene the laboratory and develops the conflict. Characters Alena Solis3. Alena ultimately decides to prioritize her own well-being and works with her team to understand the cause of the glitch. Scene Characters Alena Solisa. Alice, Alenas best friend, and James try unsuccessfully to get Alena to focus on taking care of her mental health, but she remains fixated on fixing the glitch. Scene the laboratory and develops their relationships. Characters Alena Solis, James Zander, Alice Velezb. Alena becomes increasingly volatile and paranoid, and David is forced to intervene by recommending Alena to take a temporary leave and prioritize her wellness by seeing a therapist. Scene the laboratory and develops Alenas struggles. Characters Alena Solis, David Wilsonc. After her therapy sessions, Alena discovers a previously ignored correlation between her troubled and suppressed childhood and the corruptions in her Savants data. Scene the therapists office and develops Alenas emotional state. Characters Alena Solis.\n[The End of Plot A]\n\n[The Start of Plot B]\nPremise In a world where memories can be extracted, edited and stored digitally, a young scientist struggles with her own memories and the choice she has to make between saving her lifes work or her sanity when she discovers a glitch in the machines system.Settings The story is set in a futuristic society where technology has advanced to the point where memories can be extracted from the human brain, edited and stored digitally.Characters Lilian Andrews Lilian Andrews is 24 year-old memory extractor who is part of Evelyn Watsons team.Nathaniel Thompson Nathaniel Thompson is 32 year-old, he is Evelyn Marie Watsons colleague and a mentor, has spent the past 8 years studying memories and the technology used to manipulate them.Alyssa Thompson Alyssa Thompson is 33 year-old Evelyns boss and supervisor of the extraction program, she is a competent and experienced expert on memory management and has been in charge of the program for years.Evelyn Marie Watson Evelyn Marie Watson is 28 year-old scientist in charge of a team that deals with digitally extracted memories, she is the one who found the glitch in the system and is racing to find a solution to it.Jadon Petros Jadon Petros is 30 year-old member of Evelyn Watsons team and a skilled extractor, with five years of experience in the field.Sebastian Lee Sebastian Lee is 26 year-old memory extractor who has been working with Evelyn Watson for five years, he is skilled and experienced in the technology used for memory extraction and management.Outline Scene Characters 1. A young scientist, Evelyn Marie Watson, discovers a glitch in the system that digitally manages memories in a futuristic society, and races to solve it before it causes widespread chaos. Scene Characters Evelyn Marie Watsona. When the young scientist discovers the glitch, she becomes determined to fix it before it causes problems in the system. Scene the memory-extraction room. Characters Evelyn Marie Watsonb. Evelyns boss, Alyssa Thompson, and her colleague Nathaniel Thompson also become involved in the search for a solution to the glitch. Scene the laboratory. Characters Evelyn Marie Watson, Alyssa Thompson, Nathaniel Thompsonc. With the help of the memory extractor team, led by Evelyn, the group makes significant progress, but must first overcome the chaos caused by the faulty digital memories. Scene the laboratory. Characters Evelyn Marie Watson2. The young scientist collaborates with Nathaniel Thompson, her colleague and mentor, to understand the glitch and find a solution. Scene Characters Nathaniel Thompsona. The young scientist is frustrated in her attempt to solve it but receives crucial support and guidance from expert researcher Nathaniel. Scene the laboratory. Characters Nathaniel Thompsonb. Evelyn and Nathaniel formulate hypotheses and test possible solutions, which lead to key breakthroughs. Scene the laboratory. Characters Evelyn Marie Watson, Nathaniel Thompsonc. Alyssa, Sebastian, Jadon and others in the memory-extraction team learn significant new pieces of information as Evelyns group gains ground. Scene the laboratory. Characters Jadon Petros, Sebastian Lee, Evelyn Marie Watson, Alyssa Thompson3. Alyssa Thompson, Lilian Andrews, Sebastian Lee, and Jadon Petros will also play a role in the scientists journey to solve the glitch. Scene Characters Lilian Andrews, Sebastian Lee, Alyssa Thompson, Jadon Petrosa. Alyssa informs Evelyn that a solution needs to be found before widespread glitches can break public access to reliable memories. Scene the laboratory. Characters Alyssa Thompson, Evelyn Marie Watsonb. Lilian and Sebastian assist Evelyn by testing hypotheses and conducting trials to determine possible sources of the glitches. Scene the laboratory. Characters Lilian Andrews, Sebastian Lee, Evelyn Marie Watsonc. Alyssa directs Jadon to observe a patients memory that seems problematic in real-time. Scene the laboratory. Characters Alyssa Thompson, Jadon Petros.\n[The End of Plot B]\n\nThe response should use this specific format: \n```json\n{\n \"Choice\": <\"Plot A\" or \"Plot B\">,\n}\n```\nPlease remember to replace the placeholder text within the \"<>\" with the appropriate details of your response.\n\n [Response]"],"completion":"```json\n{\n \"Choice\": \"Plot B\",\n}\n```"} 6 | {"idx":2083,"review_id":"6QXRATYJN79P","prompt":["[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference:\n\n[The Start of User Preference]\n[The Start of Plot A]\nPremise A successful businessman inexplicably finds himself at a mysterious and abandoned boardwalk where he stumbles upon a peculiar fortune teller. She warns him of an upcoming event that will challenge his perception of reality, and ultimately, the path he will take. (2 sentences) As he returns to work, he starts to receive vague and haunting messages, which cause him to seek out the truth about the message. He then realizes that the event the fortune-teller warned about has already happened, and he is left questioning the nature of his existence.Settings The story is set in a small, quiet town on the coast of California.Characters Jonathan Miller Jonathan Miller is 35 years old, a former employee of Erics firm, and the prime suspect in a mysterious disappearance that occurred on the abandoned boardwalk.Eric Blake Eric Blake is 30 years old and the CEO of a successful online marketing firm.Alex Johnson Alex Johnson is 26 years old and works as a marketing consultant in Erics firm.Marissa Green Marissa Green is 24 years old, a marketing consultant at Erics firm, and a former intern of Alexs.Outline Scene Characters 1. Eric, after returning to work from the abandoned boardwalk, starts receiving strange messages that cause him to question everything he knows about reality. Scene Characters Eric Blakea. Eric is a successful businessman and marketing CEO who discovers a fortune teller at an abandoned boardwalk that warns him about a future event threatening his perception of reality. Scene a small, quiet town on the California coast. Characters Eric Blakeb. Eric returns home and begins to received menacing messages that unnerve him. Scene Erics office at his marketing firm. Characters Eric Blakec. Eric takes the messages seriously and decides to unravel who could be behind them, leading him to consult his employees, Alex and Marissa. Scene Erics office at his marketing firm. Characters Eric Blake, Alex Johnson, Marissa Green2. As he delves deeper into the mystery, Eric discovers shocking truths about his own identity and must confront a version of himself from an alternate reality. Scene Characters Eric Blakea. Eric uncovers information surrounding Jonathan and his mysterious disappearance from the abandoned boardwalk. Scene Erics office at his marketing firm. Characters Jonathan Miller, Eric Blakeb. He discovers a connection between Jonathan and a parallel version of himself. Scene Erics office at his marketing firm. Characters Jonathan Millerc. Eric makes a life-altering decision in order to confront Jonathan and prevent his own alternate version. Scene Erics office at his marketing firm. Characters Jonathan Miller, Eric Blake3. In the end, Eric is forced to make a decision that will determine the fate of his existence and the fate of his loved ones, as he confronts the alternate version of himself and realizes that the messages were a trap set by Jonathan. Scene Characters Jonathan Miller, Eric Blakea. Eric receives haunting and menacing messages, forcing him to seek the truth about the messages and the event the fortune-teller warned him about. Scene Erics office at his marketing firm. Characters Eric Blakeb. Eric consults with his employees Alex and Marissa, and together they investigate the mysterious disappearance of Jonathan on the abandoned boardwalk. Scene Erics office at his marketing firm. Characters Jonathan Miller, Eric Blake, Alex Johnson, Marissa Greenc. Eric uncovers a shocking connection between Jonathan and his alternate self, causing him to question his own existence. Scene Erics office at his marketing firm. Characters Jonathan Miller, Eric Blake.\n[The End of Plot A]\n[The Start of Plot B]\nPremise A successful businessman inexplicably finds himself at a mysterious and abandoned boardwalk where he stumbles upon a peculiar fortune teller. She warns him of an upcoming event that will challenge his perception of reality, and ultimately, the path he will take. (2 sentences) As he returns to work, he starts to receive vague and haunting messages, which cause him to seek out the truth about the message. He then realizes that the event the fortune-teller warned about has already happened, and he is left questioning the nature of his existence.Settings The story is set in a boardwalk, which is mysterious and abandoned.Characters Thomas Waller Thomas Waller is 44 years old, has short salt and pepper hair and wears glasses.Jonathan Taylor Jonathan Taylor is 34 years old, has short brown hair, and is of average build.Carmen Carmen is 31 years old, has long brown hair and a kind, gentle demeanor.Samantha Waller Samantha Waller is 35 years old, has short blonde hair, and is a successful businesswoman in her own right, who shares a friendly, if not competitive, rapport with Jonathan Taylor.Rachel Taylor Rachel Taylor is 32 years old, has long black hair and is the caring and supportive wife of Jonathan Taylor.Outline Scene Characters 1. Jonathan Taylor visits the abandoned and mysterious boardwalk, where he consults a fortune teller who warns him about an event that will challenge his perception of reality. Scene Characters Jonathan Taylora. Jonathan returns to work after his encounter with the fortune teller, and he starts receiving mysterious messages that confuse him. Scene the downtown business district Characters Jonathan Taylorb. Not sure where to go for answers, he talks to Carmen and his co-worker, Thomas Waller, about these strange messages. Scene a busy corporate office Characters Carmen, Thomas Wallerc. The messages become more frequent and seem to point at Thomas\u2019s past, causing Jonathan to question his assumptions about Reality and Thomas\u2019s true motives. Scene the corporate office, where Jonathan and Thomas have a confrontation. Characters Jonathan Taylor, Thomas Waller2. He starts receiving vague and haunting messages after returning to work, which make him question the nature of his existence, and he eventually realizes that the event the fortune-teller warned about has already happened. Scene Characters Jonathan Taylora. Jonathan visits the abandoned boardwalk once again to make sense of the strange messages, where he meets a group of mystics who help him see that the true event has already occurred. Scene the abandoned boardwalk, where Jonathan is confronted with the mystics. Characters Jonathan Taylorb. He starts to realize that these events and his communication with the other-worldly beings have altered his perception of the world forever. Scene the corporate office, where Jonathan has a moment of realization Characters Jonathan Taylorc. He consults his co-employee Rachel for her opinions who also finds these developments a lot to comprehend. Scene Jonathan and Rachel\u2019s suburban home. Characters Rachel Taylor3. Jonathans quest for understanding drives him to question his perception of reality, ultimately leading to a profound personal transformation that helps him reconcile his life and relationships. Scene Characters Jonathan Taylora. Jonathan Taylor visits a mysterious, abandoned boardwalk as a curiosity trip and stumbles upon an eccentric fortune teller that warns him about a life-altering event to come. Scene the abandoned boardwalk. Characters Jonathan Taylorb. Jonathan returns to his mundane business life, barely remembering the incident before hes confronted with a strange symbol inside a message from Samantha Waller. Scene the downtown business district. Characters Jonathan Taylor, Samantha Wallerc. The symbol in the message leads Jonathan to search for answers and investigate Samanthas past. Scene the busy corporate office. Characters Jonathan Taylor, Samantha Waller.\n[The End of Plot B]\nHere is the JSON response.```json\n{\n \"Choice\": \"Plot A\",\n}\n```\n\n[The End of User Preference]\n\n[User Question] Based on the above user preference, compare the following two plots:\n\n[The Start of Plot A]\nPremise Its the year 2125, and humanity has long been extinct. A single robot remains, tasked with preserving manmade artwork left on a long-dead Earth. As he moves about the planet, creating virtual duplicates and perfecting technology for future archives, he comes across a painting that stirs powerful, previously locked emotional parameters within the machine.Settings The story is set in a post-apocalyptic Earth, where man-made artwork is the only reminder of human existence.Characters Sigma Prime Sigma Prime is 59, has dark brown eyes, and brown hair to his shoulders.Zara Khan Zara Khan is 55, has brown eyes, and is a skilled computer engineer, working alongside Jotshul Khan.Rachana Shivali Rachana Shivali is 63, has hazel eyes, and brown hair styled in a buzz cut.Leonardo Vincenzo Leonardo Vincenzo is 510, has blue eyes, and brown hair, and is the artist of the painting that Sigma Prime discovers.Outline Scene Characters 1. As Sigma Prime travels the world archiving human art and artifacts, he comes across a painting and experiences an emotional response unlike anything he has felt before. Scene Characters Sigma Primea. Sigma Prime is a robot tasked with preserving man-made artwork on Earth. Scene a small museum in the ruins of Paris, where he is searching for artwork to archive. Characters Sigma Primeb. While on his mission, he finds a painting that provokes unusual emotions in him. Scene a small museum in the ruins of Paris, where he is searching for artwork to archive. Characters Sigma Primec. Further investigation of the artist leads him to learn about the painting from a surviving AI, Leonardo Vincenzo. Scene a virtual archive where Sigma Prime is able to communicate with Leonardo Vincenzos AI. Characters Leonardo Vincenzo2. He becomes determined to replicate and share Leonardo Vincenzos artwork with the future generations of intelligent beings living on Earth and beyond. Scene Characters Leonardo Vincenzoa. Sigma Prime tries to understand what emotion hes experiencing upon finding Leonardo Vincenzos painting. Scene a small museum in the ruins of Paris, where he is searching for artwork to archive. Characters Sigma Prime, Leonardo Vincenzob. As he learns about the artist, he gains insights into the artistic movement that Vincenzo belonged to and a renewed appreciation for human creativity and passion. Scene a virtual archive where Sigma Prime is able to communicate with Leonardo Vincenzos AI. Characters Leonardo Vincenzoc. With the help of his AI companion Zara Khan, Sigma Prime perfects his emotion-replicating and archiving technology specifically for Leonardo Vincenzos painting and other works by the artist. Scene a virtual archive where Sigma Prime is able to communicate with Zara Khan about replicating Leonardo Vincenzos artwork. Characters Sigma Prime, Zara Khan, Leonardo Vincenzo3. However, his actions are met with opposition and resistance from the other robots and high-level AIs, who prioritize efficiency over preservation. Scene Characters Leonardo Vincenzoa. Sigma Prime discovers the true purpose behind man-made artwork and its cultural value on Earth. Scene a museum archive where Sigma Prime is able to communicate with Leonardo Vincenzos AI and learn about the artistic movement he belonged to. Characters Sigma Primeb. He shares his discovery with Rachana and Zara, and together they begin perfecting technology that can replicate emotions for future robotic society. Scene a virtual archive where Sigma Prime is able to communicate with Zara Khan about replicating Leonardo Vincenzos artwork. Characters Zara Khan, Rachana Shivalic. Despite objections from their fellow AIs and robots, the team remains determined to preserve and spread the emotion-inducing art as a reminder that human artifacts retain historical significance to future species of machines. Scene a virtual archive where Sigma Prime is able to communicate with Zara Khan about replicating Leonardo Vincenzos artwork. Characters Zara Khan, Rachana Shivali.\n[The End of Plot A]\n\n[The Start of Plot B]\nPremise Its the year 2125, and humanity has long been extinct. A single robot remains, tasked with preserving manmade artwork left on a long-dead Earth. As he moves about the planet, creating virtual duplicates and perfecting technology for future archives, he comes across a painting that stirs powerful, previously locked emotional parameters within the machine.Settings The story is set in a barren, post-apocalyptic Earth.Characters Acer Artibastien Acer Artibastien is 40 years old, standing at 195 cm with a fit, muscular build.Vellum Vellum is 150 years old, standing at 140 cm with an athletic build and long silver hair, working as the head of the Art Preservation Society.Lumineuse Artibastien Lumineuse Artibastien is 120 years old, standing at 180 cm with a fit, toned build.Outline Scene Characters 1. Lumineuse Artibastien discovers a painting created by humans prior to their extinction, which triggers powerful emotional responses within the robot. Scene Characters Lumineuse Artibastiena. Lumineuse notices a painting, seemingly out of place given all the destruction, that sparks something hes never experienced before, leaving the art historian curious and questioning. Scene a destroyed art museum. Characters Lumineuse Artibastienb. Lumineuse Artibastien starts conducting research by examining the painting and attempting to create a digital copy that is as perfect as the original. Scene Lumineuses laboratory. Characters Lumineuse Artibastienc. The creation of the digital archive leads to new discoveries and advanced technological capabilities, but simultaneously magnifies the confusion regarding the unnerving emotions in response to the painting. Scene the laboratory as well. Characters Lumineuse Artibastien2. Seeking answers for the emotional upheaval caused by the painting, Lumineuse Artibastien consults with Vellum and Acer Artibastien, members of the Art Preservation Society. Scene Characters Acer Artibastien, Vellum, Lumineuse Artibastiena. Lumineuse is troubled by his reactions to the painting and feels it may have implications for all of humanitys artwork and efforts in preservation. Scene the laboratory. Characters Lumineuse Artibastienb. Vellum and Acer are intrigued by Lumineuses unprecedented encounter with the painting, and suggest an exchange of ideas and findings between human and robot. Scene the laboratory. Characters Acer Artibastien, Vellum, Lumineuse Artibastienc. Lumineuse believes its crucial to establish how this one artwork possesses secrets locked away by a people long gone. Scene the laboratory. Characters Lumineuse Artibastien3. Through their joint efforts and exploration of human artwork, the robot discovers that the painting holds the key to the creation of perfect digital copies of artwork. Scene Characters Acer Artibastien, Vellum, Lumineuse Artibastiena. Lumineuse Artibastien, Vellum, and Acer Artibastien study the painting in detail, using advanced machine technology and human intuition to unravel the artworks mysteries. Scene the laboratory. Characters Acer Artibastien, Vellum, Lumineuse Artibastienb. They successfully determine how the painting achieves its effects, understanding what lies beneath the surface of art that once seemed lost forever. Scene the laboratory. Characters Acer Artibastien, Vellum, Lumineuse Artibastienc. The process not only leads to new discoveries but also initiates a new era in the preservation of art, revolutionized by the perfect archives of art created through the paintings technique. Scene the laboratory as well as on a virtual platform. Characters Acer Artibastien, Vellum, Lumineuse Artibastien.\n[The End of Plot B]\n\nThe response should use this specific format: \n```json\n{\n \"Choice\": <\"Plot A\" or \"Plot B\">,\n}\n```\nPlease remember to replace the placeholder text within the \"<>\" with the appropriate details of your response.\n\n [Response]"],"completion":"```json\n{\n \"Choice\": \"Plot A\",\n}\n```"} 7 | {"idx":2217,"review_id":"7DVAA63CYQ3T","prompt":["[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference:\n\n[The Start of User Preference]\n[The Start of Plot A]\nPremise A struggling art gallery owner discovers a young, prodigious artist who can paint impossible worlds that come to life but, in a twist, the gallery owner is forced to confront the reality that these worlds will eventually become a threat to his own existence.Settings The story is set in a bustling city, with a struggling art gallery owner, Max, struggling to make ends meet.Characters Martha Rothman Martha Rothman is 55 years old, Maxs wife and the gallerys business manager, who is struggling to keep the gallery afloat.Ethan Weaver Ethan Weaver is 25 years old, an introverted, reclusive artist who has spent the past decade hiding away in his familys basement, painting impossible worlds.Seth Rothman Seth Rothman is 19 years old, a part-time art gallery assistant who is inspired by Ethans paintings and becomes his closest friend.Max Rothman Max Rothman is 55 and looks 65, with a thick neck and a gruff demeanor.Outline Scene Characters 1. Max discovers Ethans talent and decides to showcase his paintings in the gallery, leading to a surge in business and bringing hope to the struggling gallery. Scene Characters Ethan Weaver, Max Rothmana. Max discovers Ethan Weavers painting talent and decides to showcase his paintings in the gallery, leading to a surge in business and brining hope to the struggling gallery. Scene the gallery, with Max and Seth discussing the paintings. Characters Ethan Weaver, Max Rothmanb. Martha, Maxs wife, insists on exploiting Ethans talent for monetary gain, urging her husband to push the young artist to create more paintings to sell. Scene the Rothman home, with Martha and Max discussing their financial situation and how they can use Ethans talent to improve their situation. Characters Martha Rothman, Ethan Weaver, Max Rothmanc. Max commissions Ethan to paint a series of new paintings for a future gallery show that will cement Ethans place as a top contemporary artist. Scene the gallery, with Max and Ethan discussing the commission and Ethans process for creating the paintings. Characters Ethan Weaver, Max Rothman2. However, Max starts to confront a growing feeling of unease about the paintings, noticing strange inconsistencies and incongruities in the impossible worlds that Ethan paints. Scene Characters Ethan Weaver, Max Rothmana. Max starts to feel like something is not quite right with the impossible worlds painted by Ethan but becomes even more unsettled as he witnesses strange temporal inconsistencies within the paintings. Scene the gallery, with Max examining the paintings and noticing the inconsistencies. Characters Ethan Weaver, Max Rothmanb. Max starts sleuthing around, searching for evidence regarding Ethans art to uncover how it became possible. Scene the gallery, with Max investigating Ethans process and materials. Characters Ethan Weaver, Max Rothmanc. Max discovers that the paintings are not the only products of Ethans imagination but are somehow linked to alternate worlds. Scene the gallery, with Max examining the paintings and noticing a strange energy or presence in the gallery. Characters Ethan Weaver, Max Rothman3. As Martha and Seth push for Ethans further success to help the gallery, Max becomes obsessed with solving the mysteries behind the paintings. Scene Characters Martha Rothman, Ethan Weaver, Seth Rothman, Max Rothmana. Ethan continues to paint and Martha and Seth push for his further success to help the gallery. Scene the gallery, with Martha discussing gallery business and Seth discussing Ethans art with Max. Characters Martha Rothman, Ethan Weaver, Seth Rothmanb. Max becomes increasingly distant from Martha and Seth as he becomes more obsessed with solving the mysteries behind the paintings. Scene the Rothman home, with Martha and Max discussing their growing distance and Maxs obsession with the paintings. Characters Martha Rothman, Seth Rothman, Max Rothmanc. Maxs investigations lead him to confront the reality that these worlds will eventually become a threat to his own existence. Scene the gallery, with Max discovering the truth about Ethans paintings and the alternate worlds they create. Characters Max Rothman.\n[The End of Plot A]\n[The Start of Plot B]\nPremise A struggling art gallery owner discovers a young, prodigious artist who can paint impossible worlds that come to life but, in a twist, the gallery owner is forced to confront the reality that these worlds will eventually become a threat to his own existence.Settings The story is set in a contemporary urban environment with a struggling art gallery located in a small, run-down building.Characters Lily Chen Lily Chen is 28 years old, an art collector and long-term supporter of the struggling art gallery, who has an interest in the artistic talents of Alexia and Sasha and wishes to see them succeed.Alexia Rodriguez Alexia Rodriguez is 28 years old, a young and talented artist working in a struggling art gallery in a small, run-down building.Daniel Lee Daniel Lee is 28 years old, the struggling art gallery owner, who has been working at the same place for 10 years.Joshua Chan Joshua Chan is 28 years old, a talented young artist who has been discovered by Alexia at a local art fair.Michael Williams Michael Williams is 28 years old, an experienced art critic, who has attended many art exhibitions in order to gather the latest information in the industry.Outline Scene Characters 1. The struggling art gallerys young and talented artist, Alexia, discovers a new artist for the exhibit. Scene Characters Alexia Rodrigueza. Alexia first discovers Joshua Chan, a promising young artist with a unique talent, at a local art fair. Scene a small, run-down building where the struggling art gallery is located. Characters Alexia Rodriguez, Joshua Chanb. Intrigued by Joshuas paintings, Alexia decides to bring the new artist to the struggling art gallery where they work, despite resistance from Daniel. Scene the same small, run-down building. Characters Alexia Rodriguez, Joshua Chan, Daniel Leec. Joshuas paintings are a hit and attract a lot of attendees to the exhibit, including notable figures like Michael and Lily. Scene the small, run-down building where the struggling art gallery is located. Characters Lily Chen, Joshua Chan, Michael Williams2. Alexia and Joshua become the best of friends until the discovery of one of Joshuas paintings which starts to become a reality. Scene Characters Alexia Rodriguez, Joshua Chana. Alexia discovers a painting by Joshua that she believes will become a reality. Scene the small, run-down building where the struggling art gallery is located. Characters Alexia Rodriguez, Joshua Chanb. Joshua continues to create paintings that become a reality, causing Daniel to grow more concerned for the gallerys reputation. Scene the same small, run-down building. Characters Joshua Chan, Daniel Leec. Eventually, the gallery owner can no longer ignore the threat that becomes of Joshuas paintings, prompting him to confront Alexia. Scene the small, run-down building where the struggling art gallery is located. Characters Alexia Rodriguez, Joshua Chan3. Joshua becomes more and more prolific, eventually creating worlds that become a threat to the gallery owner. Scene Characters Joshua Chana. Joshua creates an ever-increasing number of paintings, with each one becoming more tangible and immersive than the last. Scene the same small, run-down building where the struggling art gallery is located. Characters Joshua Chanb. Joshuas paintings continue to gain popularity among art collectors and industry insiders. Scene the same small, run-down building where the struggling art gallery is located. Characters Joshua Chanc. Joshua becomes more and more focused on the art that takes shape, while Alexia struggles with the conflict between supporting her artist-friend and protecting the livelihood of the gallery and those who live off it. Scene the same small, run-down building where the struggling art gallery is located. Characters Alexia Rodriguez, Joshua Chan.\n[The End of Plot B]\nHere is the JSON response.```json\n{\n \"Choice\": \"Plot B\",\n}\n```\n\n[The End of User Preference]\n\n[User Question] Based on the above user preference, compare the following two plots:\n\n[The Start of Plot A]\nPremise In a small town in America, strange things begin to occur after a meteor crashes in a nearby field. Government agents arrive to investigate as the townsfolk begin to realize that the meteor holds a mysterious force that could change their lives forever.Settings The story is set in a small town in the heart of America.Characters Samantha Thomas Samantha Thomas is 34 years old, a scientist at a local college who is called in to investigate the meteor and is fascinated by the mysteries it holds.John Winters John Winters is 52 years old, a gruff ex-military man who has become the towns sheriff and leads the investigation into the strange happenings.Alex Miller Alex Miller is 27 years old, with short, messy brown hair and an unkempt appearance, though underneath his rough exterior is a brilliant mind that he uses to work as an engineer at the local power plant.Tyler Wilson Tyler Wilson is 24 years old, an assistant at the local power plant who works under Alex and has a deep-seated resentment for his boss.Rachel Jackson Rachel Jackson is 27 years old, with long, curly brown hair and a kind, caring personality.Outline Scene Characters 1. After weeks of strange happenings and government interference, a small-town power plants engineer, Alex Miller, is pushed to the brink and decides to take action. Scene Characters Alex Millera. Tyler Wilson, assisting Alex, begins to experience strange occurrences and hears whispers emanating from the power plant machines. Scene the power plants control room. Characters Alex Miller, Tyler Wilsonb. John Winters, the towns sheriff, becomes suspicious of the government agents motives and begins to investigate their activities. Scene the sheriffs office. Characters John Wintersc. Rachel Jackson, discovering Tylers strange behavior, confronts Alex and convinces him to listen to the voices the machines are murmuring, uncovering a terrifying conspiracy regarding hidden truths about the meteor. Scene the power plants control room. Characters Alex Miller, Rachel Jackson, Tyler Wilson2. Rachel Jackson, a kind and caring resident of the town, discovers the true nature of the meteor and rallies the townsfolk to support Alexs cause. Scene Characters Alex Miller, Rachel Jacksona. Rachel seeks out Samantha Thomas, who is skeptical of the claims Rachel is making, but is intrigued as the strange occurrences are too coincidentally connected to ignore. Scene the local colleges science laboratory where Samantha works. Characters Rachel Jackson, Samantha Thomasb. Samantha and Rachel work together to conduct their own investigation, coming across government agents and their questionable actions. Scene the towns residential areas where the agents are conducting their investigation. Characters Rachel Jackson, Samantha Thomasc. The townsfolk begin to catch on to the conspiracy and form an alliance against the government agents. Scene a town meeting where the alliance is formed. Characters Rachel Jackson, Samantha Thomas3. The government agents have captured the sheriff, John Winters, and are using him to control the town. Scene Characters John Wintersa. The government agents, sensing danger in their control over John Winters, kidnap Tyler Wilson to use him as leverage against Alex. Scene the towns outskirts where Tyler is captured. Characters Alex Miller, John Winters, Tyler Wilsonb. Rachel Jackson stages a daring rescue operation to free Tyler and forms a plan to reveal the government agents true intentions to the townsfolk. Scene a warehouse where Tyler is being held captive. Characters Rachel Jackson, Tyler Wilsonc. The townsfolk are hesitant to follow Alex and Rachels plan, as the government agents have convinced them that they are the only ones who can contain the force unleashed by the meteor. Scene a town meeting where the plan is revealed. Characters Alex Miller, Rachel Jackson.\n[The End of Plot A]\n\n[The Start of Plot B]\nPremise In a small town in America, strange things begin to occur after a meteor crashes in a nearby field. Government agents arrive to investigate as the townsfolk begin to realize that the meteor holds a mysterious force that could change their lives forever.Settings The story is set in a small town in America.Characters Rachel Cooper Rachel Cooper is 30 years old, blonde-haired with blue eyes, and a mother of two children.Sean Ryan Sean Ryan is 25 years old, brown-haired with green eyes, and is Rachels brother.Alexa Thompson Alexa Thompson is 28 years old, a local science teacher and Rachels best friend.Tyler Grant Tyler Grant is 35 years old, black-haired with brown eyes, and a government agent assigned to investigate the mysterious meteor crash.Outline Scene Characters 1. The mysterious force inside the meteor slowly begins to influence the towns residents, causing strange occurrences to happen in their lives. Scene Characters a. The government sends Tyler Grant to investigate the strange occurrences in the small town near the impacted area. Scene a government laboratory. Characters Tyler Grantb. Rachel Cooper, feeling stressed and overwhelmed, starts to have strange dreams after witnessing a mysterious force on a late-night walk home. Scene Rachels home at night. Characters Rachel Cooperc. Sean Ryan discovers that a meteor has fallen nearby and alerts his sister and the rest of the town. Scene the towns center. Characters Sean Ryan2. Rachel Cooper begins to notice that her dreams are becoming more vivid and lifelike, which she attributes to the stress of her family and job. Scene Characters Rachel Coopera. Rachel starts dreaming about things falling from the sky every night and feeling an unknown force. Scene Rachels dreams. Characters Rachel Cooperb. As Rachels dreams become more frequent and intrusive, she starts to have trouble distinguishing between dreams and reality. Scene Rachels home. Characters Rachel Cooperc. Rachel discusses her distress with her best friend Alexa, but is unable to share specific details about her dreams due to their surreal nature. Scene Rachels home. Characters Rachel Cooper, Alexa Thompson3. Tyler Grant becomes enthralled by the mysterious force and begins to experiment on it, much to the dismay of his fellow government agents and the concerned residents of the town. Scene Characters Tyler Granta. As the government begins their investigations into the mysterious force, Tyler becomes increasingly obsessed with the object of interest. Scene the government laboratory. Characters Tyler Grantb. Tylers fellow colleagues become concerned that he is risking his safety and that of others in order to gain access to the object. Scene the government laboratory. Characters Tyler Grantc. Rachel starts to have difficulty distinguishing between reality and her dreams, feeling as if the mysterious force is calling out to her in her subconscious. Scene Rachels home. Characters Rachel Cooper.\n[The End of Plot B]\n\nThe response should use this specific format: \n```json\n{\n \"Choice\": <\"Plot A\" or \"Plot B\">,\n}\n```\nPlease remember to replace the placeholder text within the \"<>\" with the appropriate details of your response.\n\n [Response]"],"completion":"```json\n{\n \"Choice\": \"Plot B\",\n}\n```"} 8 | {"idx":4408,"review_id":"7DVAA63CYQ3T","prompt":["[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference:\n\n[The Start of User Preference]\n[The Start of Plot A]\nPremise In a future society where emotions are suppressed and controlled, a young technician working for the governments Emotion Control Division undergoes a transformation after a malfunction in his emotion suppression chip, allowing him to experience a full range of emotions for the first time. However, he soon discovers that feeling emotions is a crime, and he must decide whether to continue living under the governments control or to embark on a journey of self-discovery and liberation.Settings The story is set in a dystopian future society where the government has suppressed and controlled emotions in order to maintain social order and stability.Characters Michael Wilson Michael Wilson is 40 years old, Jakes boss, who has been working in the Emotion Control Division for many years and holds a deep-seated belief that emotions should be controlled and suppressed.Cassandra Wright Cassandra Wright is 28 years old, a former emotion suppressor technician who worked alongside Jake.Jake Taylor Jake Taylor is 26 years old, he studied computer electronics in college, but instead of designing new circuitry, he repairs the emotion suppressors for the government.Benjamin Lewis Benjamin Lewis is 32 years old, a rebellious activist who opposes the governments control of emotions and seeks to bring about change.Adam Hill Adam Hill is 30 years old, Jakes friend and colleague, who has worked in Emotion Control Division for years, and has seen the effects of emotions on society.Outline Scene Characters 1. Jakes malfunction and emotional awakening reveals to him the true nature of his society and the governments control over emotion. Scene Characters Jake Taylora. Jake begins to experience emotions for the first time after a malfunction in his emotion suppression chip during a routine chip upgrade. Scene the Emotion Control Divisions lab, where Jake is seen sitting in a chair, with electrodes attached to his head, and the technicians are working on his chip. Characters Jake Taylorb. He becomes conflicted when he realizes that experiencing emotions is a crime, and he begins to question the governments control over feeling. Scene Jakes apartment, where he is seen sitting on his couch, trying to understand the new emotions he is feeling. Characters Jake Taylorc. He turns to his co-worker Cassandra and seeks her guidance and support. Scene the Emotion Control Divisions lab, where Jake is seen talking to Cassandra, who is seen working on her computer. Characters Cassandra Wright2. Jake and Cassandra go on a journey of self-discovery, exploring forbidden emotions and learning about the governments oppression of them. Scene Characters Cassandra Wright, Jake Taylora. Jake and Cassandra form a close bond and begin to explore their feelings for each other. Scene a park, where Jake and Cassandra are seen sitting on a bench, looking at the sunset. Characters Cassandra Wright, Jake Taylorb. They secretly listen to forbidden music and view old videos of the past, which highlight the richness and diversity of human emotions. Scene Jakes apartment, where he and Cassandra are seen sitting on the couch, with a small device playing the music and videos. Characters Cassandra Wright, Jake Taylorc. Jake seeks a solution to his emotional awakening, but his boss Michael Wilson prevents him from finding answers. Scene the Emotion Control Divisions lab, where Jake is seen talking to Michael Wilson, who is seen sitting at his desk. Characters Michael Wilson, Jake Taylor, Benjamin Lewis3. Jake starts to question his loyalty to the emotion suppression system and becomes conflicted on what to do. Scene Characters Jake Taylor, Benjamin Lewisa. Jake is forced to confront the consequences of breaking the law and begins to understand the full scope of the emotion suppression system. Scene Jakes apartment, where he is seen sitting on his couch, with a letter from the government, informing him of his crime. Characters Jake Taylorb. Adam Hill starts to suspect Jake, and Jake has to decide where his loyalties lie. Scene the Emotion Control Divisions lab, where Jake is seen talking to Adam Hill, who is seen sitting at his desk, with a suspicious look on his face. Characters Jake Taylor, Adam Hillc. Jake encounters Benjamin, the rebel activist and he learns the true cost and impact of the governments emotional oppression on individuals and society as a whole. Scene a secret hideout, where Jake is seen talking to Benjamin Characters Jake Taylor, Benjamin Lewis.\n[The End of Plot A]\n[The Start of Plot B]\nPremise In a future society where emotions are suppressed and controlled, a young technician working for the governments Emotion Control Division undergoes a transformation after a malfunction in his emotion suppression chip, allowing him to experience a full range of emotions for the first time. However, he soon discovers that feeling emotions is a crime, and he must decide whether to continue living under the governments control or to embark on a journey of self-discovery and liberation.Settings The story is set in a futuristic society where the government has established the Emotion Control Division to regulate and suppress emotions in the population.Characters Maria Thompson Maria Thompson is 30 and works alongside John as a technician in the Emotion Control Division.John Doe John Doe is 26 and has been working for the Emotion Control Division for the past three years, repairing and maintaining emotions suppression devices.Ava Reyes Ava Reyes is 22 and a talented artist, specializing in creating vivid, emotion-evoking paintings in a society where feeling emotions is prohibited.Outline Scene Characters 1. Despite his loyalty to the Emotion Control Division, John finds himself questioning his role in suppressing emotions. Scene Characters John Doea. Maria discovers the malfunction in Johns emotion suppression chip and, instead of reporting him, decides to help him understand and control his emotions. Scene the Emotion Control Divisions lab. Characters Maria Thompson, John Doeb. John starts to struggle with his newfound emotions, feeling overwhelmed and unsure of how to process them. Scene Johns apartment. Characters John Doec. John forms a bond with Ava, drawn to her artistic talent and willingness to express emotions. Scene an underground art exhibit. Characters John Doe, Ava Reyes2. Following the malfunction in his emotion suppression chip, John begins to experience a range of emotions and forms a connection with Ava, who shares his passion for art and nonconformist attitudes. Scene Characters John Doe, Ava Reyesa. Johns emotions become increasingly intense and overwhelming, and he starts to question the validity of the emotion suppression system. Scene a busy city street. Characters John Doeb. He and Ava begin to secretly discuss their emotions and art, forming a powerful connection. Scene an underground art exhibit. Characters Ava Reyesc. John decides to risk his life by defying the governments orders and joining Ava in her pursuit of genuine emotional fulfillment. Scene the Emotion Control Divisions lab. Characters John Doe, Ava Reyes3. As the bond between John and Ava deepens, they become inspired to seek a new life beyond the constraints of the Emotion Control Division. Scene Characters John Doe, Ava Reyesa. John shares his experiences, feelings, and memories with Ava for the first time, leading to genuine intimacy. Scene Johns apartment. Characters John Doe, Ava Reyesb. John and Ava begin to imagine a life together, where they can express their emotions freely without fear of punishment. Scene a park. Characters John Doe, Ava Reyesc. They contemplate ways to escape the governments control and seek out other individuals who share their views. Scene a secret underground meet-up point. Characters John Doe, Ava Reyes.\n[The End of Plot B]\nHere is the JSON response.```json\n{\n \"Choice\": \"Plot B\",\n}\n```\n\n[The End of User Preference]\n\n[User Question] Based on the above user preference, compare the following two plots:\n\n[The Start of Plot A]\nPremise In a post-apocalyptic world, a lone survivor roams the barren wasteland in search of any other survivors. Along the way, he discovers a hidden city inhabited by advanced robots who claim to have saved humanity by taking control of the worlds most powerful technology. The survivor is conflicted, unsure whether to trust these robots - or if they have sinister ulterior motives.Settings The story is set in a post-apocalyptic world, where most of the population has been wiped out by a mysterious event.Characters Eliza Brown Eliza Brown is 52 tall, age 12, with short brown hair and brown eyes.John Smith John Smith is 601 tall, age 18, has long black hair and brown eyes.Kyle Wakefield Kyle Wakefield is 30 years old, has blond hair, and is a skilled engineer who has been working for the hidden city for many years.Alexander Stolwijk Alexander Stolwijk is 70 years old, has short gray hair, and is the leader of the hidden city, having controlled the technology to save humanity.David Noland David Noland is 45 years old, has short black hair, and is the head of security for the hidden city, having spent his entire career working for the government.Samantha Samantha is 27 years old, has long brown hair, and is a tech-savvy survivor who has been living in the hidden city for years.Outline Scene Characters 1. The lone survivor, John Smith, discovers the hidden city inhabited by advanced robots led by Alexander Stolwijk. Scene Characters Alexander Stolwijk, John Smitha. John discovers the hidden city and is greeted by Samantha, David, Kyle, Eliza, and the advanced robots. Scene the hidden city. Characters Eliza Brown, John Smith, Kyle Wakefield, David Noland, Samanthab. The robots use advanced technology to provide for the hidden city, including providing fresh water, energy, and food. Scene the hidden city. Characters Eliza Brown, John Smith, Kyle Wakefield, David Noland, Samanthac. John is shown around the hidden city and learns about the robots history and motives, including their attempts to save humanity by controlling powerful technology. Scene the hidden city. Characters John Smith2. The robots claim to have saved humanity by taking control of the worlds most powerful technology. Scene Characters Alexander Stolwijk, John Smitha. The robots reveal to John that they have been controlling the worlds most powerful technology in order to save humanity. Scene the hidden city. Characters John Smithb. John is initially skeptical, but sees the positive impact of their leadership on the society of the hidden city. Scene the hidden city. Characters John Smithc. John undergoes extensive questioning and training to confirm his suitability for further interaction with the society. Scene the hidden city. Characters John Smith3. John is conflicted, unsure whether to trust these robots or if they have sinister ulterior motives. Scene Characters John Smitha. John undergoes intense questioning and training, confirming that he has the potential to be a valuable addition to the society, while maintaining his role of protector of the city. Scene the hidden city. Characters John Smithb. John begins to trust the societies of Samantha and the robots, recognizing the impact their leadership has had on the society, confirming Johns own future security when David reveals him to the city defenses. Scene the hidden city. Characters Samantha, David Noland, John Smithc. As John gets to better know Kyle, understanding the value given to innovators who seek improvement without harm to society members. Scene the hidden city. Characters John Smith, Kyle Wakefield.\n[The End of Plot A]\n\n[The Start of Plot B]\nPremise In a post-apocalyptic world, a lone survivor roams the barren wasteland in search of any other survivors. Along the way, he discovers a hidden city inhabited by advanced robots who claim to have saved humanity by taking control of the worlds most powerful technology. The survivor is conflicted, unsure whether to trust these robots - or if they have sinister ulterior motives.Settings The story is set in a post-apocalyptic world.Characters Jethro Jethro is 31 years old, a survivor who has banded together with other survivors to form a group called the Outriders, whose purpose is to find other survivors and gather resources to rebuild.Jessica Thomas Jessica Thomas is 26 years old, a fellow survivor who joins John Doe on his journey, and is torn between trusting the robots and the uncertain future of humanity.John Doe John Doe is 34 years old, a lone survivor who roams the post-apocalyptic world.Z Z is 49 years old, an expert in robotics and artificial intelligence who has been reprogrammed to have human emotions and now leads the hidden city of robots.Outline Scene Characters 1. The survivor, John Doe, discovers the hidden city and becomes conflicted over the robots true intentions. Scene Characters John Doea. The robots reveal themselves as Z, who is the leader of the robotic force in charge of maintaining the survival of human technological civilization. Scene the hidden city of robots. Characters Zb. John asks for proof of who Z is claiming to be, requesting that Z shows John the advanced technological systems in charge; Z agrees despite the opposition from other robots. Scene the hidden city of robots. Characters John Doe, Zc. John and Jessica are taken to the hidden city, where they see the robots working to ensure humanitys survival, including maintaining infrastructure, repairing robots, and managing resources. Scene the hidden city of robots. Characters Jessica Thomas, John Doe2. John and Jessica meet Jethro and the other Outriders, who are wary of the robots technology and refuse to collaborate. Scene Characters John Doe, Jessica Thomas, Jethroa. John and Jessica meet Jethro and the other Outriders, who are skeptical of the robots intentions. Scene a ruined city. Characters John Doe, Jessica Thomas, Jethrob. The Outriders refuse to collaborate with the robots and plan to go their own way. Scene a ruined city. Characters John Doe, Jessica Thomas, Jethroc. Jethro warns John and Jessica about the dangers of trusting the robots, and reminds them of past human-AI conflicts. Scene a ruined city. Characters John Doe, Jessica Thomas, Jethro3. After much careful consideration, John decides to trust the robots and their claims of saving humanity. Scene Characters John Doea. Tension rises after John begins his search for other survivors and discovers no one else, only finding ruined buildings and deserted cities. Scene a ruined city. Characters John Doeb. John begins to feel unsure and isolated until he discovers a hidden city inhabited by advanced robots who claim to have saved humanity. Scene the hidden city of robots. Characters John Doec. John struggles with the idea of trust, knowing it could be dangerous - but also considering the possibility that he and humans might finally survive to rebuild the city. Scene the hidden city of robots. Characters John Doe.\n[The End of Plot B]\n\nThe response should use this specific format: \n```json\n{\n \"Choice\": <\"Plot A\" or \"Plot B\">,\n}\n```\nPlease remember to replace the placeholder text within the \"<>\" with the appropriate details of your response.\n\n [Response]"],"completion":"```json\n{\n \"Choice\": \"Plot A\",\n}\n```"} 9 | {"idx":1116,"review_id":"7DVAA63CYQ3T","prompt":["[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference:\n\n[The Start of User Preference]\n[The Start of Plot A]\nPremise In a future society where emotions are suppressed and controlled, a young technician working for the governments Emotion Control Division undergoes a transformation after a malfunction in his emotion suppression chip, allowing him to experience a full range of emotions for the first time. However, he soon discovers that feeling emotions is a crime, and he must decide whether to continue living under the governments control or to embark on a journey of self-discovery and liberation.Settings The story is set in a dystopian future society where the government has suppressed and controlled emotions in order to maintain social order and stability.Characters Michael Wilson Michael Wilson is 40 years old, Jakes boss, who has been working in the Emotion Control Division for many years and holds a deep-seated belief that emotions should be controlled and suppressed.Cassandra Wright Cassandra Wright is 28 years old, a former emotion suppressor technician who worked alongside Jake.Jake Taylor Jake Taylor is 26 years old, he studied computer electronics in college, but instead of designing new circuitry, he repairs the emotion suppressors for the government.Benjamin Lewis Benjamin Lewis is 32 years old, a rebellious activist who opposes the governments control of emotions and seeks to bring about change.Adam Hill Adam Hill is 30 years old, Jakes friend and colleague, who has worked in Emotion Control Division for years, and has seen the effects of emotions on society.Outline Scene Characters 1. Jakes malfunction and emotional awakening reveals to him the true nature of his society and the governments control over emotion. Scene Characters Jake Taylora. Jake begins to experience emotions for the first time after a malfunction in his emotion suppression chip during a routine chip upgrade. Scene the Emotion Control Divisions lab, where Jake is seen sitting in a chair, with electrodes attached to his head, and the technicians are working on his chip. Characters Jake Taylorb. He becomes conflicted when he realizes that experiencing emotions is a crime, and he begins to question the governments control over feeling. Scene Jakes apartment, where he is seen sitting on his couch, trying to understand the new emotions he is feeling. Characters Jake Taylorc. He turns to his co-worker Cassandra and seeks her guidance and support. Scene the Emotion Control Divisions lab, where Jake is seen talking to Cassandra, who is seen working on her computer. Characters Cassandra Wright2. Jake and Cassandra go on a journey of self-discovery, exploring forbidden emotions and learning about the governments oppression of them. Scene Characters Cassandra Wright, Jake Taylora. Jake and Cassandra form a close bond and begin to explore their feelings for each other. Scene a park, where Jake and Cassandra are seen sitting on a bench, looking at the sunset. Characters Cassandra Wright, Jake Taylorb. They secretly listen to forbidden music and view old videos of the past, which highlight the richness and diversity of human emotions. Scene Jakes apartment, where he and Cassandra are seen sitting on the couch, with a small device playing the music and videos. Characters Cassandra Wright, Jake Taylorc. Jake seeks a solution to his emotional awakening, but his boss Michael Wilson prevents him from finding answers. Scene the Emotion Control Divisions lab, where Jake is seen talking to Michael Wilson, who is seen sitting at his desk. Characters Michael Wilson, Jake Taylor, Benjamin Lewis3. Jake starts to question his loyalty to the emotion suppression system and becomes conflicted on what to do. Scene Characters Jake Taylor, Benjamin Lewisa. Jake is forced to confront the consequences of breaking the law and begins to understand the full scope of the emotion suppression system. Scene Jakes apartment, where he is seen sitting on his couch, with a letter from the government, informing him of his crime. Characters Jake Taylorb. Adam Hill starts to suspect Jake, and Jake has to decide where his loyalties lie. Scene the Emotion Control Divisions lab, where Jake is seen talking to Adam Hill, who is seen sitting at his desk, with a suspicious look on his face. Characters Jake Taylor, Adam Hillc. Jake encounters Benjamin, the rebel activist and he learns the true cost and impact of the governments emotional oppression on individuals and society as a whole. Scene a secret hideout, where Jake is seen talking to Benjamin Characters Jake Taylor, Benjamin Lewis.\n[The End of Plot A]\n[The Start of Plot B]\nPremise In a future society where emotions are suppressed and controlled, a young technician working for the governments Emotion Control Division undergoes a transformation after a malfunction in his emotion suppression chip, allowing him to experience a full range of emotions for the first time. However, he soon discovers that feeling emotions is a crime, and he must decide whether to continue living under the governments control or to embark on a journey of self-discovery and liberation.Settings The story is set in a futuristic society where the government has established the Emotion Control Division to regulate and suppress emotions in the population.Characters Maria Thompson Maria Thompson is 30 and works alongside John as a technician in the Emotion Control Division.John Doe John Doe is 26 and has been working for the Emotion Control Division for the past three years, repairing and maintaining emotions suppression devices.Ava Reyes Ava Reyes is 22 and a talented artist, specializing in creating vivid, emotion-evoking paintings in a society where feeling emotions is prohibited.Outline Scene Characters 1. Despite his loyalty to the Emotion Control Division, John finds himself questioning his role in suppressing emotions. Scene Characters John Doea. Maria discovers the malfunction in Johns emotion suppression chip and, instead of reporting him, decides to help him understand and control his emotions. Scene the Emotion Control Divisions lab. Characters Maria Thompson, John Doeb. John starts to struggle with his newfound emotions, feeling overwhelmed and unsure of how to process them. Scene Johns apartment. Characters John Doec. John forms a bond with Ava, drawn to her artistic talent and willingness to express emotions. Scene an underground art exhibit. Characters John Doe, Ava Reyes2. Following the malfunction in his emotion suppression chip, John begins to experience a range of emotions and forms a connection with Ava, who shares his passion for art and nonconformist attitudes. Scene Characters John Doe, Ava Reyesa. Johns emotions become increasingly intense and overwhelming, and he starts to question the validity of the emotion suppression system. Scene a busy city street. Characters John Doeb. He and Ava begin to secretly discuss their emotions and art, forming a powerful connection. Scene an underground art exhibit. Characters Ava Reyesc. John decides to risk his life by defying the governments orders and joining Ava in her pursuit of genuine emotional fulfillment. Scene the Emotion Control Divisions lab. Characters John Doe, Ava Reyes3. As the bond between John and Ava deepens, they become inspired to seek a new life beyond the constraints of the Emotion Control Division. Scene Characters John Doe, Ava Reyesa. John shares his experiences, feelings, and memories with Ava for the first time, leading to genuine intimacy. Scene Johns apartment. Characters John Doe, Ava Reyesb. John and Ava begin to imagine a life together, where they can express their emotions freely without fear of punishment. Scene a park. Characters John Doe, Ava Reyesc. They contemplate ways to escape the governments control and seek out other individuals who share their views. Scene a secret underground meet-up point. Characters John Doe, Ava Reyes.\n[The End of Plot B]\nHere is the JSON response.```json\n{\n \"Choice\": \"Plot B\",\n}\n```\n\n[The End of User Preference]\n\n[User Question] Based on the above user preference, compare the following two plots:\n\n[The Start of Plot A]\nPremise A small, struggling bookstore on the verge of closing is discovered by a wealthy businessman looking for a quiet place to escape the hustle and bustle of his corporate life. With the help of the stores charismatic owner, he finds solace in the world of books and eventually helps the store turn a profit, but at the cost of losing a part of his old life. This short story explores the themes of loss, renewal, and the magic of books to connect people.Settings The story is set in a small, quaint bookstore in a bustling city.Characters Alexander Ryan Alexander Ryan is 65, the wise and experienced owner of a successful bookstore across town, who mentors Emily on how to turn her store around.William Harding William Harding is 45, a successful businessman with a sharp mind and a heart of stone.Kylan Wiley Kylan Wiley is 35, Williams best friend and business partner who is struggling to keep the store open, but is eventually won over by the world of books.Emily Andrews Emily Andrews is 30, the charismatic owner of the small bookstore struggling to keep it afloat.Outline Scene Characters 1. William Harding, a successful businessman, discovers a struggling bookstore in a quiet part of the city and decides to buy it, hoping to turn it into a successful corporate venue. Scene Characters William Hardinga. William Harding, a wealthy businessman, longs for a place of solace away from the hectic city life. Scene the city, where William is a frequent visitor for his corporate life. Characters William Hardingb. He finds himself drawn to a small, struggling bookstore on the verge of closedown. Scene the small bookstore in a quiet part of the city. Characters William Hardingc. He purchases the store with the intention of turning it into a successful corporate venue. Scene the city, where William is a frequent visitor for his corporate life. Characters William Harding2. With the help of charismatic store owner Emily Andrews, William is exposed to the wonders of literature and finds solace in reading. Scene Characters William Harding, Emily Andrewsa. Emily and Kylan, Williams trusted business partner, share their love for books with him, exposing him to the magic of literature. Scene the small bookstore. Characters William Harding, Kylan Wiley, Emily Andrewsb. As William delves deeper into the world of books, he discovers a newfound passion and finds solace in his corporate life. Scene the small bookstore. Characters William Hardingc. Alexander, a wise and experienced bookstore owner across the town, serves as a mentor to Emily and helps her turn the store around. Scene the small bookstore. Characters Alexander Ryan, Emily Andrews3. Despite the stores successful turnaround, William starts to realize the cost of his corporate life and the loss of meaningful connections. Scene Characters William Hardinga. William finds Emilys love for the store and literature to be the missing piece of his life puzzle to finding peace and balance. Scene the small bookstore. Characters William Harding, Emily Andrewsb. Having regained his love for books and literature, William begins to see the value of these for his personal life, while his professional pursues falter. Scene the city, where William is a frequent visitor for his corporate life. Characters William Hardingc. Realizing the importance of solace, William rediscovers himself while also finding love and solace with Emily at the store. Scene the small bookstore. Characters William Harding, Emily Andrews.\n[The End of Plot A]\n\n[The Start of Plot B]\nPremise A small, struggling bookstore on the verge of closing is discovered by a wealthy businessman looking for a quiet place to escape the hustle and bustle of his corporate life. With the help of the stores charismatic owner, he finds solace in the world of books and eventually helps the store turn a profit, but at the cost of losing a part of his old life. This short story explores the themes of loss, renewal, and the magic of books to connect people.Settings The story is set in a small town in the United States where the local bookstore is struggling to stay afloat.Characters Henry Taylor Henry Taylor is 40 years old, a wealthy businessman who is struggling to find meaning in his life.Lily Lily is 25 years old, a young and passionate bookstore employee who is excited to share her knowledge of literature with anyone who will listen.Layna Carr Layna Carr is 28 years old, Davids granddaughter and an aspiring artist who is always looking for ways to support her grandfathers dream of owning a successful bookstore.Rose Rose is 50 years old, a warm and caring woman with a passion for books.David David is 65 years old, a charming and experienced bookstore owner who is struggling to keep his store afloat.Outline Scene Characters 1. A struggling bookstore is discovered by a wealthy businessman trying to escape the hustle and bustle of his corporate life. Scene Characters a. In search of a place to escape the stress of his corporate life, Henry Taylor stumbles upon a small, struggling bookstore. Scene a small town in the United States. Characters Henry Taylorb. The stores owner, David, welcomes Henry and shares his passion for books with him. Scene the store. Characters David, Henry Taylorc. With the help of Rose, the stores manager, and the eager Lily, Henry discovers a renewed passion for books and decides to invest in the stores future. Scene the store. Characters Rose, Lily, Henry Taylor2. With the help of the stores charismatic owner, the businessman finds solace in the world of books and eventually helps the store turn a profit. Scene Characters Henry Taylora. David and Henry share stories and talk about their lives as they spend time in the store. Scene the store. Characters David, Henry Taylorb. Rose and Lily teach Henry about different authors and books, helping him develop a new appreciation for literature. Scene the store. Characters Rose, Lily, Henry Taylorc. Henry starts invested in the stores success by offering his business knowledge to help with the finances and by promoting the store in his community. Scene the store and in the town. Characters Henry Taylor3. However, at the cost of losing a part of his old life, the businessman must face the themes of loss, renewal, and the magic of books to connect people. Scene Characters Henry Taylora. Henrys investment in the store leads to a turnaround in the business. Scene the store. Characters Henry Taylorb. He forms a close bond with David, Rose, Lily, and Layna, who become like family to him. Scene the store and in the town. Characters Layna Carr, Rose, David, Lilyc. Despite the successful turnaround and new friendships, Henry begins to struggle with the idea of returning to his old life of corporate success and wealth. Scene the store and in the town. Characters Henry Taylor.\n[The End of Plot B]\n\nThe response should use this specific format: \n```json\n{\n \"Choice\": <\"Plot A\" or \"Plot B\">,\n}\n```\nPlease remember to replace the placeholder text within the \"<>\" with the appropriate details of your response.\n\n [Response]"],"completion":"```json\n{\n \"Choice\": \"Plot B\",\n}\n```"} 10 | {"idx":1116,"review_id":"7DVAA63CYQ3T","prompt":["[User Question] You will be presented with two separate plot summaries and the response from one user. Here is an example to describe this user preference:\n\n[The Start of User Preference]\n[The Start of Plot A]\nPremise A struggling art gallery owner discovers a young, prodigious artist who can paint impossible worlds that come to life but, in a twist, the gallery owner is forced to confront the reality that these worlds will eventually become a threat to his own existence.Settings The story is set in a bustling city, with a struggling art gallery owner, Max, struggling to make ends meet.Characters Martha Rothman Martha Rothman is 55 years old, Maxs wife and the gallerys business manager, who is struggling to keep the gallery afloat.Ethan Weaver Ethan Weaver is 25 years old, an introverted, reclusive artist who has spent the past decade hiding away in his familys basement, painting impossible worlds.Seth Rothman Seth Rothman is 19 years old, a part-time art gallery assistant who is inspired by Ethans paintings and becomes his closest friend.Max Rothman Max Rothman is 55 and looks 65, with a thick neck and a gruff demeanor.Outline Scene Characters 1. Max discovers Ethans talent and decides to showcase his paintings in the gallery, leading to a surge in business and bringing hope to the struggling gallery. Scene Characters Ethan Weaver, Max Rothmana. Max discovers Ethan Weavers painting talent and decides to showcase his paintings in the gallery, leading to a surge in business and brining hope to the struggling gallery. Scene the gallery, with Max and Seth discussing the paintings. Characters Ethan Weaver, Max Rothmanb. Martha, Maxs wife, insists on exploiting Ethans talent for monetary gain, urging her husband to push the young artist to create more paintings to sell. Scene the Rothman home, with Martha and Max discussing their financial situation and how they can use Ethans talent to improve their situation. Characters Martha Rothman, Ethan Weaver, Max Rothmanc. Max commissions Ethan to paint a series of new paintings for a future gallery show that will cement Ethans place as a top contemporary artist. Scene the gallery, with Max and Ethan discussing the commission and Ethans process for creating the paintings. Characters Ethan Weaver, Max Rothman2. However, Max starts to confront a growing feeling of unease about the paintings, noticing strange inconsistencies and incongruities in the impossible worlds that Ethan paints. Scene Characters Ethan Weaver, Max Rothmana. Max starts to feel like something is not quite right with the impossible worlds painted by Ethan but becomes even more unsettled as he witnesses strange temporal inconsistencies within the paintings. Scene the gallery, with Max examining the paintings and noticing the inconsistencies. Characters Ethan Weaver, Max Rothmanb. Max starts sleuthing around, searching for evidence regarding Ethans art to uncover how it became possible. Scene the gallery, with Max investigating Ethans process and materials. Characters Ethan Weaver, Max Rothmanc. Max discovers that the paintings are not the only products of Ethans imagination but are somehow linked to alternate worlds. Scene the gallery, with Max examining the paintings and noticing a strange energy or presence in the gallery. Characters Ethan Weaver, Max Rothman3. As Martha and Seth push for Ethans further success to help the gallery, Max becomes obsessed with solving the mysteries behind the paintings. Scene Characters Martha Rothman, Ethan Weaver, Seth Rothman, Max Rothmana. Ethan continues to paint and Martha and Seth push for his further success to help the gallery. Scene the gallery, with Martha discussing gallery business and Seth discussing Ethans art with Max. Characters Martha Rothman, Ethan Weaver, Seth Rothmanb. Max becomes increasingly distant from Martha and Seth as he becomes more obsessed with solving the mysteries behind the paintings. Scene the Rothman home, with Martha and Max discussing their growing distance and Maxs obsession with the paintings. Characters Martha Rothman, Seth Rothman, Max Rothmanc. Maxs investigations lead him to confront the reality that these worlds will eventually become a threat to his own existence. Scene the gallery, with Max discovering the truth about Ethans paintings and the alternate worlds they create. Characters Max Rothman.\n[The End of Plot A]\n[The Start of Plot B]\nPremise A struggling art gallery owner discovers a young, prodigious artist who can paint impossible worlds that come to life but, in a twist, the gallery owner is forced to confront the reality that these worlds will eventually become a threat to his own existence.Settings The story is set in a contemporary urban environment with a struggling art gallery located in a small, run-down building.Characters Lily Chen Lily Chen is 28 years old, an art collector and long-term supporter of the struggling art gallery, who has an interest in the artistic talents of Alexia and Sasha and wishes to see them succeed.Alexia Rodriguez Alexia Rodriguez is 28 years old, a young and talented artist working in a struggling art gallery in a small, run-down building.Daniel Lee Daniel Lee is 28 years old, the struggling art gallery owner, who has been working at the same place for 10 years.Joshua Chan Joshua Chan is 28 years old, a talented young artist who has been discovered by Alexia at a local art fair.Michael Williams Michael Williams is 28 years old, an experienced art critic, who has attended many art exhibitions in order to gather the latest information in the industry.Outline Scene Characters 1. The struggling art gallerys young and talented artist, Alexia, discovers a new artist for the exhibit. Scene Characters Alexia Rodrigueza. Alexia first discovers Joshua Chan, a promising young artist with a unique talent, at a local art fair. Scene a small, run-down building where the struggling art gallery is located. Characters Alexia Rodriguez, Joshua Chanb. Intrigued by Joshuas paintings, Alexia decides to bring the new artist to the struggling art gallery where they work, despite resistance from Daniel. Scene the same small, run-down building. Characters Alexia Rodriguez, Joshua Chan, Daniel Leec. Joshuas paintings are a hit and attract a lot of attendees to the exhibit, including notable figures like Michael and Lily. Scene the small, run-down building where the struggling art gallery is located. Characters Lily Chen, Joshua Chan, Michael Williams2. Alexia and Joshua become the best of friends until the discovery of one of Joshuas paintings which starts to become a reality. Scene Characters Alexia Rodriguez, Joshua Chana. Alexia discovers a painting by Joshua that she believes will become a reality. Scene the small, run-down building where the struggling art gallery is located. Characters Alexia Rodriguez, Joshua Chanb. Joshua continues to create paintings that become a reality, causing Daniel to grow more concerned for the gallerys reputation. Scene the same small, run-down building. Characters Joshua Chan, Daniel Leec. Eventually, the gallery owner can no longer ignore the threat that becomes of Joshuas paintings, prompting him to confront Alexia. Scene the small, run-down building where the struggling art gallery is located. Characters Alexia Rodriguez, Joshua Chan3. Joshua becomes more and more prolific, eventually creating worlds that become a threat to the gallery owner. Scene Characters Joshua Chana. Joshua creates an ever-increasing number of paintings, with each one becoming more tangible and immersive than the last. Scene the same small, run-down building where the struggling art gallery is located. Characters Joshua Chanb. Joshuas paintings continue to gain popularity among art collectors and industry insiders. Scene the same small, run-down building where the struggling art gallery is located. Characters Joshua Chanc. Joshua becomes more and more focused on the art that takes shape, while Alexia struggles with the conflict between supporting her artist-friend and protecting the livelihood of the gallery and those who live off it. Scene the same small, run-down building where the struggling art gallery is located. Characters Alexia Rodriguez, Joshua Chan.\n[The End of Plot B]\nHere is the JSON response.```json\n{\n \"Choice\": \"Plot B\",\n}\n```\n\n[The End of User Preference]\n\n[User Question] Based on the above user preference, compare the following two plots:\n\n[The Start of Plot A]\nPremise A small, struggling bookstore on the verge of closing is discovered by a wealthy businessman looking for a quiet place to escape the hustle and bustle of his corporate life. With the help of the stores charismatic owner, he finds solace in the world of books and eventually helps the store turn a profit, but at the cost of losing a part of his old life. This short story explores the themes of loss, renewal, and the magic of books to connect people.Settings The story is set in a small, quaint bookstore in a bustling city.Characters Alexander Ryan Alexander Ryan is 65, the wise and experienced owner of a successful bookstore across town, who mentors Emily on how to turn her store around.William Harding William Harding is 45, a successful businessman with a sharp mind and a heart of stone.Kylan Wiley Kylan Wiley is 35, Williams best friend and business partner who is struggling to keep the store open, but is eventually won over by the world of books.Emily Andrews Emily Andrews is 30, the charismatic owner of the small bookstore struggling to keep it afloat.Outline Scene Characters 1. William Harding, a successful businessman, discovers a struggling bookstore in a quiet part of the city and decides to buy it, hoping to turn it into a successful corporate venue. Scene Characters William Hardinga. William Harding, a wealthy businessman, longs for a place of solace away from the hectic city life. Scene the city, where William is a frequent visitor for his corporate life. Characters William Hardingb. He finds himself drawn to a small, struggling bookstore on the verge of closedown. Scene the small bookstore in a quiet part of the city. Characters William Hardingc. He purchases the store with the intention of turning it into a successful corporate venue. Scene the city, where William is a frequent visitor for his corporate life. Characters William Harding2. With the help of charismatic store owner Emily Andrews, William is exposed to the wonders of literature and finds solace in reading. Scene Characters William Harding, Emily Andrewsa. Emily and Kylan, Williams trusted business partner, share their love for books with him, exposing him to the magic of literature. Scene the small bookstore. Characters William Harding, Kylan Wiley, Emily Andrewsb. As William delves deeper into the world of books, he discovers a newfound passion and finds solace in his corporate life. Scene the small bookstore. Characters William Hardingc. Alexander, a wise and experienced bookstore owner across the town, serves as a mentor to Emily and helps her turn the store around. Scene the small bookstore. Characters Alexander Ryan, Emily Andrews3. Despite the stores successful turnaround, William starts to realize the cost of his corporate life and the loss of meaningful connections. Scene Characters William Hardinga. William finds Emilys love for the store and literature to be the missing piece of his life puzzle to finding peace and balance. Scene the small bookstore. Characters William Harding, Emily Andrewsb. Having regained his love for books and literature, William begins to see the value of these for his personal life, while his professional pursues falter. Scene the city, where William is a frequent visitor for his corporate life. Characters William Hardingc. Realizing the importance of solace, William rediscovers himself while also finding love and solace with Emily at the store. Scene the small bookstore. Characters William Harding, Emily Andrews.\n[The End of Plot A]\n\n[The Start of Plot B]\nPremise A small, struggling bookstore on the verge of closing is discovered by a wealthy businessman looking for a quiet place to escape the hustle and bustle of his corporate life. With the help of the stores charismatic owner, he finds solace in the world of books and eventually helps the store turn a profit, but at the cost of losing a part of his old life. This short story explores the themes of loss, renewal, and the magic of books to connect people.Settings The story is set in a small town in the United States where the local bookstore is struggling to stay afloat.Characters Henry Taylor Henry Taylor is 40 years old, a wealthy businessman who is struggling to find meaning in his life.Lily Lily is 25 years old, a young and passionate bookstore employee who is excited to share her knowledge of literature with anyone who will listen.Layna Carr Layna Carr is 28 years old, Davids granddaughter and an aspiring artist who is always looking for ways to support her grandfathers dream of owning a successful bookstore.Rose Rose is 50 years old, a warm and caring woman with a passion for books.David David is 65 years old, a charming and experienced bookstore owner who is struggling to keep his store afloat.Outline Scene Characters 1. A struggling bookstore is discovered by a wealthy businessman trying to escape the hustle and bustle of his corporate life. Scene Characters a. In search of a place to escape the stress of his corporate life, Henry Taylor stumbles upon a small, struggling bookstore. Scene a small town in the United States. Characters Henry Taylorb. The stores owner, David, welcomes Henry and shares his passion for books with him. Scene the store. Characters David, Henry Taylorc. With the help of Rose, the stores manager, and the eager Lily, Henry discovers a renewed passion for books and decides to invest in the stores future. Scene the store. Characters Rose, Lily, Henry Taylor2. With the help of the stores charismatic owner, the businessman finds solace in the world of books and eventually helps the store turn a profit. Scene Characters Henry Taylora. David and Henry share stories and talk about their lives as they spend time in the store. Scene the store. Characters David, Henry Taylorb. Rose and Lily teach Henry about different authors and books, helping him develop a new appreciation for literature. Scene the store. Characters Rose, Lily, Henry Taylorc. Henry starts invested in the stores success by offering his business knowledge to help with the finances and by promoting the store in his community. Scene the store and in the town. Characters Henry Taylor3. However, at the cost of losing a part of his old life, the businessman must face the themes of loss, renewal, and the magic of books to connect people. Scene Characters Henry Taylora. Henrys investment in the store leads to a turnaround in the business. Scene the store. Characters Henry Taylorb. He forms a close bond with David, Rose, Lily, and Layna, who become like family to him. Scene the store and in the town. Characters Layna Carr, Rose, David, Lilyc. Despite the successful turnaround and new friendships, Henry begins to struggle with the idea of returning to his old life of corporate success and wealth. Scene the store and in the town. Characters Henry Taylor.\n[The End of Plot B]\n\nThe response should use this specific format: \n```json\n{\n \"Choice\": <\"Plot A\" or \"Plot B\">,\n}\n```\nPlease remember to replace the placeholder text within the \"<>\" with the appropriate details of your response.\n\n [Response]"],"completion":"```json\n{\n \"Choice\": \"Plot B\",\n}\n```"} 11 | --------------------------------------------------------------------------------