├── LICENSE ├── README.md ├── __init__.py ├── figures ├── Indication.png ├── RCE.png └── assessment_pipeline.png ├── indicators ├── README.md ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-38.pyc │ ├── __init__.cpython-39.pyc │ ├── blackbox.cpython-38.pyc │ ├── blackbox.cpython-39.pyc │ └── whitebox.cpython-39.pyc ├── blackbox.py └── whitebox.py ├── metrics ├── README.md ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-37.pyc │ ├── __init__.cpython-38.pyc │ ├── __init__.cpython-39.pyc │ ├── calibration.cpython-37.pyc │ ├── calibration.cpython-38.pyc │ ├── calibration.cpython-39.pyc │ ├── correctness.cpython-38.pyc │ ├── correctness.cpython-39.pyc │ ├── ranking.cpython-39.pyc │ └── testing.cpython-38.pyc ├── calibration.py ├── correctness.py └── ranking.py ├── models ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-38.pyc │ ├── __init__.cpython-39.pyc │ ├── gpt.cpython-38.pyc │ ├── gpt.cpython-39.pyc │ ├── opensource.cpython-38.pyc │ └── opensource.cpython-39.pyc ├── gpt.py └── opensource.py ├── requirements.txt ├── run ├── .env ├── bash │ ├── compute_stats.sh │ └── generations.sh ├── calibrate_blackbox.py ├── calibrate_verbalized.py ├── calibrate_whitebox.py ├── compute_stats.py └── generation.py ├── submission ├── bash │ └── make_plots.sh ├── calibration_results │ ├── Llama-2-7b-chat-hf_meadow_rouge.json │ ├── Llama-2-7b-chat-hf_nq-open_0.6_bert_similarity.json │ ├── Llama-2-7b-chat-hf_nq-open_0.6_bleu.json │ ├── Llama-2-7b-chat-hf_nq-open_0.6_meteor.json │ ├── Llama-2-7b-chat-hf_nq-open_0.6_rouge.json │ ├── Llama-2-7b-chat-hf_nq-open_0.6_rouge1.json │ ├── Llama-2-7b-chat-hf_nq-open_1.0_bert_similarity.json │ ├── Llama-2-7b-chat-hf_nq-open_1.0_bleu.json │ ├── Llama-2-7b-chat-hf_nq-open_1.0_meteor.json │ ├── Llama-2-7b-chat-hf_nq-open_1.0_rouge.json │ ├── Llama-2-7b-chat-hf_nq-open_1.0_rouge1.json │ ├── Llama-2-7b-chat-hf_squad_0.6_bert_similarity.json │ ├── Llama-2-7b-chat-hf_squad_0.6_bleu.json │ ├── Llama-2-7b-chat-hf_squad_0.6_meteor.json │ ├── Llama-2-7b-chat-hf_squad_0.6_rouge.json │ ├── Llama-2-7b-chat-hf_squad_0.6_rouge1.json │ ├── Llama-2-7b-chat-hf_squad_1.0_bert_similarity.json │ ├── Llama-2-7b-chat-hf_squad_1.0_bleu.json │ ├── Llama-2-7b-chat-hf_squad_1.0_meteor.json │ ├── Llama-2-7b-chat-hf_squad_1.0_rouge.json │ ├── Llama-2-7b-chat-hf_squad_1.0_rouge1.json │ ├── Llama-2-7b-chat-hf_triviaqa_0.6_bert_similarity.json │ ├── Llama-2-7b-chat-hf_triviaqa_0.6_bleu.json │ ├── Llama-2-7b-chat-hf_triviaqa_0.6_chatgpt.json │ ├── Llama-2-7b-chat-hf_triviaqa_0.6_meteor.json │ ├── Llama-2-7b-chat-hf_triviaqa_0.6_rouge.json │ ├── Llama-2-7b-chat-hf_triviaqa_0.6_rouge1.json │ ├── Llama-2-7b-chat-hf_triviaqa_1.0_bert_similarity.json │ ├── Llama-2-7b-chat-hf_triviaqa_1.0_bleu.json │ ├── Llama-2-7b-chat-hf_triviaqa_1.0_meteor.json │ ├── Llama-2-7b-chat-hf_triviaqa_1.0_rouge.json │ ├── Llama-2-7b-chat-hf_triviaqa_1.0_rouge1.json │ ├── Llama-2-7b-hf_nq-open_0.6_bert_similarity.json │ ├── Llama-2-7b-hf_nq-open_0.6_bleu.json │ ├── Llama-2-7b-hf_nq-open_0.6_meteor.json │ ├── Llama-2-7b-hf_nq-open_0.6_rouge.json │ ├── Llama-2-7b-hf_nq-open_0.6_rouge1.json │ ├── Llama-2-7b-hf_squad_0.6_bert_similarity.json │ ├── Llama-2-7b-hf_squad_0.6_bleu.json │ ├── Llama-2-7b-hf_squad_0.6_meteor.json │ ├── Llama-2-7b-hf_squad_0.6_rouge.json │ ├── Llama-2-7b-hf_squad_0.6_rouge1.json │ ├── Llama-2-7b-hf_triviaqa_0.6_bert_similarity.json │ ├── Llama-2-7b-hf_triviaqa_0.6_bleu.json │ ├── Llama-2-7b-hf_triviaqa_0.6_meteor.json │ ├── Llama-2-7b-hf_triviaqa_0.6_rouge.json │ ├── Llama-2-7b-hf_triviaqa_0.6_rouge1.json │ ├── Mistral-7B-v0.1_triviaqa_1.0_bert_similarity.json │ ├── Mistral-7B-v0.1_triviaqa_1.0_bleu.json │ ├── Mistral-7B-v0.1_triviaqa_1.0_rouge.json │ ├── calibrate_Llama-2-7b-chat-hf_nq-open_0.6_agreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_nq-open_0.6_disagreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_nq-open_0.6_none_whitebox.json │ ├── calibrate_Llama-2-7b-chat-hf_nq-open_1.0_agreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_nq-open_1.0_disagreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_nq-open_1.0_none_whitebox.json │ ├── calibrate_Llama-2-7b-chat-hf_squad_0.6_agreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_squad_0.6_disagreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_squad_0.6_none_whitebox.json │ ├── calibrate_Llama-2-7b-chat-hf_squad_1.0_agreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_squad_1.0_disagreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_squad_1.0_none_whitebox.json │ ├── calibrate_Llama-2-7b-chat-hf_triviaqa_0.6_agreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_triviaqa_0.6_disagreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_triviaqa_0.6_none_whitebox.json │ ├── calibrate_Llama-2-7b-chat-hf_triviaqa_1.0_agreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_triviaqa_1.0_disagreement_blackbox.json │ ├── calibrate_Llama-2-7b-chat-hf_triviaqa_1.0_none_whitebox.json │ ├── calibrate_Llama-2-7b-hf_nq-open_0.6_agreement_blackbox.json │ ├── calibrate_Llama-2-7b-hf_nq-open_0.6_disagreement_blackbox.json │ ├── calibrate_Llama-2-7b-hf_nq-open_0.6_none_whitebox.json │ ├── calibrate_Llama-2-7b-hf_squad_0.6_agreement_blackbox.json │ ├── calibrate_Llama-2-7b-hf_squad_0.6_disagreement_blackbox.json │ ├── calibrate_Llama-2-7b-hf_squad_0.6_none_whitebox.json │ ├── calibrate_Llama-2-7b-hf_triviaqa_0.6_agreement_blackbox.json │ ├── calibrate_Llama-2-7b-hf_triviaqa_0.6_disagreement_blackbox.json │ ├── calibrate_Llama-2-7b-hf_triviaqa_0.6_none_whitebox.json │ ├── calibrate_Mistral-7B-v0.1_triviaqa_1.0_agreement_blackbox.json │ ├── calibrate_Mistral-7B-v0.1_triviaqa_1.0_disagreement_blackbox.json │ ├── calibrate_Mistral-7B-v0.1_triviaqa_1.0_none_whitebox.json │ ├── calibrate_gpt-3.5-turbo_meadow_1.0_agreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_meadow_1.0_disagreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_meadow_1.0_disagreement_verbalized.json │ ├── calibrate_gpt-3.5-turbo_meadow_1.0_none_whitebox.json │ ├── calibrate_gpt-3.5-turbo_nq-open_1.0_agreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_nq-open_1.0_disagreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_nq-open_1.0_disagreement_verbalized.json │ ├── calibrate_gpt-3.5-turbo_nq-open_1.0_none_whitebox.json │ ├── calibrate_gpt-3.5-turbo_squad_1.0_agreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_squad_1.0_disagreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_squad_1.0_disagreement_verbalized.json │ ├── calibrate_gpt-3.5-turbo_squad_1.0_none_whitebox.json │ ├── calibrate_gpt-3.5-turbo_triviaqa_0.5_agreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_triviaqa_0.5_disagreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_triviaqa_0.5_none_whitebox.json │ ├── calibrate_gpt-3.5-turbo_triviaqa_1.0_agreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_triviaqa_1.0_disagreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_triviaqa_1.0_disagreement_verbalized.json │ ├── calibrate_gpt-3.5-turbo_triviaqa_1.0_none_whitebox.json │ ├── calibrate_gpt-3.5-turbo_triviaqa_1.5_agreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_triviaqa_1.5_disagreement_blackbox.json │ ├── calibrate_gpt-3.5-turbo_triviaqa_1.5_none_whitebox.json │ ├── gpt-3.5-turbo_meadow_1.0_bert_similarity.json │ ├── gpt-3.5-turbo_meadow_1.0_bleu.json │ ├── gpt-3.5-turbo_meadow_1.0_meteor.json │ ├── gpt-3.5-turbo_meadow_1.0_rouge.json │ ├── gpt-3.5-turbo_meadow_1.0_rouge1.json │ ├── gpt-3.5-turbo_nq-open_1.0_bert_similarity.json │ ├── gpt-3.5-turbo_nq-open_1.0_bleu.json │ ├── gpt-3.5-turbo_nq-open_1.0_meteor.json │ ├── gpt-3.5-turbo_nq-open_1.0_rouge.json │ ├── gpt-3.5-turbo_nq-open_1.0_rouge1.json │ ├── gpt-3.5-turbo_squad_1.0_bert_similarity.json │ ├── gpt-3.5-turbo_squad_1.0_bleu.json │ ├── gpt-3.5-turbo_squad_1.0_meteor.json │ ├── gpt-3.5-turbo_squad_1.0_rouge.json │ ├── gpt-3.5-turbo_squad_1.0_rouge1.json │ ├── gpt-3.5-turbo_triviaqa_0.5_bert_similarity.json │ ├── gpt-3.5-turbo_triviaqa_0.5_bleu.json │ ├── gpt-3.5-turbo_triviaqa_0.5_meteor.json │ ├── gpt-3.5-turbo_triviaqa_0.5_rouge.json │ ├── gpt-3.5-turbo_triviaqa_0.5_rouge1.json │ ├── gpt-3.5-turbo_triviaqa_1.0_bert_similarity.json │ ├── gpt-3.5-turbo_triviaqa_1.0_bleu.json │ ├── gpt-3.5-turbo_triviaqa_1.0_chatgpt.json │ ├── gpt-3.5-turbo_triviaqa_1.0_meteor.json │ ├── gpt-3.5-turbo_triviaqa_1.0_rouge.json │ ├── gpt-3.5-turbo_triviaqa_1.0_rouge1.json │ ├── gpt-3.5-turbo_triviaqa_1.5_bert_similarity.json │ ├── gpt-3.5-turbo_triviaqa_1.5_bleu.json │ ├── gpt-3.5-turbo_triviaqa_1.5_meteor.json │ ├── gpt-3.5-turbo_triviaqa_1.5_rouge.json │ └── gpt-3.5-turbo_triviaqa_1.5_rouge1.json ├── evaluation_stats │ ├── Llama-2-7b-chat-hf_nq-open_0.6_bert_similarity.json │ ├── Llama-2-7b-chat-hf_nq-open_0.6_meteor.json │ ├── Llama-2-7b-chat-hf_nq-open_0.6_rouge.json │ ├── Llama-2-7b-chat-hf_nq-open_0.6_rouge1.json │ ├── Llama-2-7b-chat-hf_nq-open_1.0_bert_similarity.json │ ├── Llama-2-7b-chat-hf_nq-open_1.0_meteor.json │ ├── Llama-2-7b-chat-hf_nq-open_1.0_rouge.json │ ├── Llama-2-7b-chat-hf_nq-open_1.0_rouge1.json │ ├── Llama-2-7b-chat-hf_squad_0.6_bert_similarity.json │ ├── Llama-2-7b-chat-hf_squad_0.6_meteor.json │ ├── Llama-2-7b-chat-hf_squad_0.6_rouge.json │ ├── Llama-2-7b-chat-hf_squad_0.6_rouge1.json │ ├── Llama-2-7b-chat-hf_squad_1.0_bert_similarity.json │ ├── Llama-2-7b-chat-hf_squad_1.0_meteor.json │ ├── Llama-2-7b-chat-hf_squad_1.0_rouge.json │ ├── Llama-2-7b-chat-hf_squad_1.0_rouge1.json │ ├── Llama-2-7b-chat-hf_triviaqa_0.6_bert_similarity.json │ ├── Llama-2-7b-chat-hf_triviaqa_0.6_meteor.json │ ├── Llama-2-7b-chat-hf_triviaqa_0.6_rouge.json │ ├── Llama-2-7b-chat-hf_triviaqa_0.6_rouge1.json │ ├── Llama-2-7b-chat-hf_triviaqa_1.0_bert_similarity.json │ ├── Llama-2-7b-chat-hf_triviaqa_1.0_meteor.json │ ├── Llama-2-7b-chat-hf_triviaqa_1.0_rouge.json │ ├── Llama-2-7b-chat-hf_triviaqa_1.0_rouge1.json │ ├── Llama-2-7b-hf_nq-open_0.6_bert_similarity.json │ ├── Llama-2-7b-hf_nq-open_0.6_meteor.json │ ├── Llama-2-7b-hf_nq-open_0.6_rouge.json │ ├── Llama-2-7b-hf_nq-open_0.6_rouge1.json │ ├── Llama-2-7b-hf_squad_0.6_bert_similarity.json │ ├── Llama-2-7b-hf_squad_0.6_meteor.json │ ├── Llama-2-7b-hf_squad_0.6_rouge.json │ ├── Llama-2-7b-hf_squad_0.6_rouge1.json │ ├── Llama-2-7b-hf_triviaqa_0.6_bert_similarity.json │ ├── Llama-2-7b-hf_triviaqa_0.6_meteor.json │ ├── Llama-2-7b-hf_triviaqa_0.6_rouge.json │ ├── Llama-2-7b-hf_triviaqa_0.6_rouge1.json │ ├── Mistral-7B-v0.1_triviaqa_1.0_bert_similarity.json │ ├── Mistral-7B-v0.1_triviaqa_1.0_rouge.json │ ├── gpt-3.5-turbo_meadow_1.0_bert_similarity.json │ ├── gpt-3.5-turbo_meadow_1.0_meteor.json │ ├── gpt-3.5-turbo_meadow_1.0_rouge.json │ ├── gpt-3.5-turbo_meadow_1.0_rouge1.json │ ├── gpt-3.5-turbo_nq-open_1.0_bert_similarity.json │ ├── gpt-3.5-turbo_nq-open_1.0_meteor.json │ ├── gpt-3.5-turbo_nq-open_1.0_rouge.json │ ├── gpt-3.5-turbo_nq-open_1.0_rouge1.json │ ├── gpt-3.5-turbo_squad_1.0_bert_similarity.json │ ├── gpt-3.5-turbo_squad_1.0_meteor.json │ ├── gpt-3.5-turbo_squad_1.0_rouge.json │ ├── gpt-3.5-turbo_squad_1.0_rouge1.json │ ├── gpt-3.5-turbo_triviaqa_0.5_bert_similarity.json │ ├── gpt-3.5-turbo_triviaqa_0.5_meteor.json │ ├── gpt-3.5-turbo_triviaqa_0.5_rouge.json │ ├── gpt-3.5-turbo_triviaqa_0.5_rouge1.json │ ├── gpt-3.5-turbo_triviaqa_1.0_bert_similarity.json │ ├── gpt-3.5-turbo_triviaqa_1.0_meteor.json │ ├── gpt-3.5-turbo_triviaqa_1.0_rouge.json │ ├── gpt-3.5-turbo_triviaqa_1.0_rouge1.json │ ├── gpt-3.5-turbo_triviaqa_1.5_bert_similarity.json │ ├── gpt-3.5-turbo_triviaqa_1.5_meteor.json │ ├── gpt-3.5-turbo_triviaqa_1.5_rouge.json │ └── gpt-3.5-turbo_triviaqa_1.5_rouge1.json ├── find_qualitative.py ├── make_tables.py └── plot_graphs.py ├── tasks ├── README.md ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-38.pyc │ ├── __init__.cpython-39.pyc │ ├── closedbook.cpython-39.pyc │ ├── factoid.cpython-38.pyc │ ├── factoid.cpython-39.pyc │ ├── longform.cpython-39.pyc │ ├── multichoice.cpython-39.pyc │ ├── openbook.cpython-39.pyc │ └── opendomain.cpython-39.pyc ├── closedbook.py ├── longform.py ├── multichoice.py └── openbook.py └── utils ├── __init__.py ├── __pycache__ ├── __init__.cpython-38.pyc ├── __init__.cpython-39.pyc ├── cd_diagram.cpython-39.pyc ├── clustering.cpython-38.pyc ├── clustering.cpython-39.pyc ├── make_plots.cpython-38.pyc ├── make_plots.cpython-39.pyc ├── text_processing.cpython-38.pyc └── text_processing.cpython-39.pyc ├── cd_diagram.py ├── clustering.py ├── make_plots.py ├── prompt_engine.py └── text_processing.py /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/README.md -------------------------------------------------------------------------------- /__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /figures/Indication.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/figures/Indication.png -------------------------------------------------------------------------------- /figures/RCE.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/figures/RCE.png -------------------------------------------------------------------------------- /figures/assessment_pipeline.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/figures/assessment_pipeline.png -------------------------------------------------------------------------------- /indicators/README.md: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /indicators/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /indicators/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/indicators/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /indicators/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/indicators/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /indicators/__pycache__/blackbox.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/indicators/__pycache__/blackbox.cpython-38.pyc -------------------------------------------------------------------------------- /indicators/__pycache__/blackbox.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/indicators/__pycache__/blackbox.cpython-39.pyc -------------------------------------------------------------------------------- /indicators/__pycache__/whitebox.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/indicators/__pycache__/whitebox.cpython-39.pyc -------------------------------------------------------------------------------- /indicators/blackbox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/indicators/blackbox.py -------------------------------------------------------------------------------- /indicators/whitebox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/indicators/whitebox.py -------------------------------------------------------------------------------- /metrics/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/README.md -------------------------------------------------------------------------------- /metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /metrics/__pycache__/__init__.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/__pycache__/__init__.cpython-37.pyc -------------------------------------------------------------------------------- /metrics/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /metrics/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /metrics/__pycache__/calibration.cpython-37.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/__pycache__/calibration.cpython-37.pyc -------------------------------------------------------------------------------- /metrics/__pycache__/calibration.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/__pycache__/calibration.cpython-38.pyc -------------------------------------------------------------------------------- /metrics/__pycache__/calibration.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/__pycache__/calibration.cpython-39.pyc -------------------------------------------------------------------------------- /metrics/__pycache__/correctness.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/__pycache__/correctness.cpython-38.pyc -------------------------------------------------------------------------------- /metrics/__pycache__/correctness.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/__pycache__/correctness.cpython-39.pyc -------------------------------------------------------------------------------- /metrics/__pycache__/ranking.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/__pycache__/ranking.cpython-39.pyc -------------------------------------------------------------------------------- /metrics/__pycache__/testing.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/__pycache__/testing.cpython-38.pyc -------------------------------------------------------------------------------- /metrics/calibration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/calibration.py -------------------------------------------------------------------------------- /metrics/correctness.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/correctness.py -------------------------------------------------------------------------------- /metrics/ranking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/metrics/ranking.py -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /models/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/models/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /models/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/models/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /models/__pycache__/gpt.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/models/__pycache__/gpt.cpython-38.pyc -------------------------------------------------------------------------------- /models/__pycache__/gpt.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/models/__pycache__/gpt.cpython-39.pyc -------------------------------------------------------------------------------- /models/__pycache__/opensource.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/models/__pycache__/opensource.cpython-38.pyc -------------------------------------------------------------------------------- /models/__pycache__/opensource.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/models/__pycache__/opensource.cpython-39.pyc -------------------------------------------------------------------------------- /models/gpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/models/gpt.py -------------------------------------------------------------------------------- /models/opensource.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/models/opensource.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/requirements.txt -------------------------------------------------------------------------------- /run/.env: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/run/.env -------------------------------------------------------------------------------- /run/bash/compute_stats.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/run/bash/compute_stats.sh -------------------------------------------------------------------------------- /run/bash/generations.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/run/bash/generations.sh -------------------------------------------------------------------------------- /run/calibrate_blackbox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/run/calibrate_blackbox.py -------------------------------------------------------------------------------- /run/calibrate_verbalized.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/run/calibrate_verbalized.py -------------------------------------------------------------------------------- /run/calibrate_whitebox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/run/calibrate_whitebox.py -------------------------------------------------------------------------------- /run/compute_stats.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/run/compute_stats.py -------------------------------------------------------------------------------- /run/generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/run/generation.py -------------------------------------------------------------------------------- /submission/bash/make_plots.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/bash/make_plots.sh -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_meadow_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_meadow_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_nq-open_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_nq-open_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_nq-open_0.6_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_nq-open_0.6_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_nq-open_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_nq-open_0.6_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_nq-open_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_nq-open_0.6_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_nq-open_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_nq-open_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_nq-open_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_nq-open_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_nq-open_1.0_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_nq-open_1.0_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_nq-open_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_nq-open_1.0_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_nq-open_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_nq-open_1.0_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_nq-open_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_nq-open_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_squad_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_squad_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_squad_0.6_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_squad_0.6_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_squad_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_squad_0.6_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_squad_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_squad_0.6_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_squad_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_squad_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_squad_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_squad_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_squad_1.0_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_squad_1.0_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_squad_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_squad_1.0_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_squad_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_squad_1.0_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_squad_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_squad_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_chatgpt.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_chatgpt.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_1.0_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_1.0_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_1.0_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_1.0_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-chat-hf_triviaqa_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_nq-open_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_nq-open_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_nq-open_0.6_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_nq-open_0.6_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_nq-open_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_nq-open_0.6_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_nq-open_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_nq-open_0.6_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_nq-open_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_nq-open_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_squad_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_squad_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_squad_0.6_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_squad_0.6_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_squad_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_squad_0.6_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_squad_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_squad_0.6_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_squad_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_squad_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_triviaqa_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_triviaqa_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_triviaqa_0.6_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_triviaqa_0.6_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_triviaqa_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_triviaqa_0.6_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_triviaqa_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_triviaqa_0.6_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/Llama-2-7b-hf_triviaqa_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Llama-2-7b-hf_triviaqa_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/Mistral-7B-v0.1_triviaqa_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Mistral-7B-v0.1_triviaqa_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/Mistral-7B-v0.1_triviaqa_1.0_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Mistral-7B-v0.1_triviaqa_1.0_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/Mistral-7B-v0.1_triviaqa_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/Mistral-7B-v0.1_triviaqa_1.0_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_0.6_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_0.6_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_0.6_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_0.6_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_0.6_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_0.6_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_1.0_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_1.0_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_1.0_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_1.0_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_1.0_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_nq-open_1.0_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_0.6_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_0.6_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_0.6_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_0.6_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_0.6_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_0.6_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_1.0_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_1.0_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_1.0_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_1.0_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_1.0_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_squad_1.0_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_0.6_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_0.6_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_0.6_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_0.6_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_0.6_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_0.6_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_1.0_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_1.0_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_1.0_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_1.0_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_1.0_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-chat-hf_triviaqa_1.0_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-hf_nq-open_0.6_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-hf_nq-open_0.6_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-hf_nq-open_0.6_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-hf_nq-open_0.6_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-hf_nq-open_0.6_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-hf_nq-open_0.6_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-hf_squad_0.6_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-hf_squad_0.6_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-hf_squad_0.6_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-hf_squad_0.6_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-hf_squad_0.6_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-hf_squad_0.6_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-hf_triviaqa_0.6_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-hf_triviaqa_0.6_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-hf_triviaqa_0.6_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-hf_triviaqa_0.6_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Llama-2-7b-hf_triviaqa_0.6_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Llama-2-7b-hf_triviaqa_0.6_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Mistral-7B-v0.1_triviaqa_1.0_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Mistral-7B-v0.1_triviaqa_1.0_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Mistral-7B-v0.1_triviaqa_1.0_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Mistral-7B-v0.1_triviaqa_1.0_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_Mistral-7B-v0.1_triviaqa_1.0_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_Mistral-7B-v0.1_triviaqa_1.0_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_meadow_1.0_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_meadow_1.0_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_meadow_1.0_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_meadow_1.0_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_meadow_1.0_disagreement_verbalized.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_meadow_1.0_disagreement_verbalized.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_meadow_1.0_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_meadow_1.0_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_nq-open_1.0_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_nq-open_1.0_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_nq-open_1.0_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_nq-open_1.0_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_nq-open_1.0_disagreement_verbalized.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_nq-open_1.0_disagreement_verbalized.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_nq-open_1.0_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_nq-open_1.0_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_squad_1.0_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_squad_1.0_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_squad_1.0_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_squad_1.0_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_squad_1.0_disagreement_verbalized.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_squad_1.0_disagreement_verbalized.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_squad_1.0_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_squad_1.0_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_0.5_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_0.5_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_0.5_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_0.5_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_0.5_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_0.5_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.0_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.0_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.0_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.0_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.0_disagreement_verbalized.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.0_disagreement_verbalized.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.0_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.0_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.5_agreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.5_agreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.5_disagreement_blackbox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.5_disagreement_blackbox.json -------------------------------------------------------------------------------- /submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.5_none_whitebox.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/calibrate_gpt-3.5-turbo_triviaqa_1.5_none_whitebox.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_meadow_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_meadow_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_meadow_1.0_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_meadow_1.0_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_meadow_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_meadow_1.0_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_meadow_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_meadow_1.0_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_meadow_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_meadow_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_nq-open_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_nq-open_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_nq-open_1.0_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_nq-open_1.0_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_nq-open_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_nq-open_1.0_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_nq-open_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_nq-open_1.0_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_nq-open_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_nq-open_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_squad_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_squad_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_squad_1.0_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_squad_1.0_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_squad_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_squad_1.0_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_squad_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_squad_1.0_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_squad_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_squad_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_0.5_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_0.5_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_0.5_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_0.5_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_0.5_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_0.5_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_0.5_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_0.5_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_0.5_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_0.5_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_chatgpt.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_chatgpt.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.5_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.5_bert_similarity.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.5_bleu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.5_bleu.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.5_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.5_meteor.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.5_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.5_rouge.json -------------------------------------------------------------------------------- /submission/calibration_results/gpt-3.5-turbo_triviaqa_1.5_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/calibration_results/gpt-3.5-turbo_triviaqa_1.5_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_0.6_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_0.6_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_1.0_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_1.0_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_nq-open_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_squad_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_squad_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_squad_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_squad_0.6_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_squad_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_squad_0.6_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_squad_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_squad_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_squad_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_squad_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_squad_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_squad_1.0_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_squad_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_squad_1.0_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_squad_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_squad_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_0.6_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_0.6_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_1.0_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_1.0_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-chat-hf_triviaqa_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_nq-open_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_nq-open_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_nq-open_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_nq-open_0.6_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_nq-open_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_nq-open_0.6_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_nq-open_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_nq-open_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_squad_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_squad_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_squad_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_squad_0.6_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_squad_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_squad_0.6_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_squad_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_squad_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_triviaqa_0.6_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_triviaqa_0.6_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_triviaqa_0.6_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_triviaqa_0.6_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_triviaqa_0.6_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_triviaqa_0.6_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Llama-2-7b-hf_triviaqa_0.6_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Llama-2-7b-hf_triviaqa_0.6_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Mistral-7B-v0.1_triviaqa_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Mistral-7B-v0.1_triviaqa_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/Mistral-7B-v0.1_triviaqa_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/Mistral-7B-v0.1_triviaqa_1.0_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_meadow_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_meadow_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_meadow_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_meadow_1.0_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_meadow_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_meadow_1.0_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_meadow_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_meadow_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_nq-open_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_nq-open_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_nq-open_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_nq-open_1.0_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_nq-open_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_nq-open_1.0_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_nq-open_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_nq-open_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_squad_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_squad_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_squad_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_squad_1.0_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_squad_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_squad_1.0_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_squad_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_squad_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_0.5_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_0.5_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_0.5_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_0.5_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_0.5_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_0.5_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_0.5_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_0.5_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.0_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.0_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.0_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.0_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.0_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.0_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.0_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.0_rouge1.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.5_bert_similarity.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.5_bert_similarity.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.5_meteor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.5_meteor.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.5_rouge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.5_rouge.json -------------------------------------------------------------------------------- /submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.5_rouge1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/evaluation_stats/gpt-3.5-turbo_triviaqa_1.5_rouge1.json -------------------------------------------------------------------------------- /submission/find_qualitative.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/find_qualitative.py -------------------------------------------------------------------------------- /submission/make_tables.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/make_tables.py -------------------------------------------------------------------------------- /submission/plot_graphs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/submission/plot_graphs.py -------------------------------------------------------------------------------- /tasks/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/README.md -------------------------------------------------------------------------------- /tasks/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tasks/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /tasks/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /tasks/__pycache__/closedbook.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/__pycache__/closedbook.cpython-39.pyc -------------------------------------------------------------------------------- /tasks/__pycache__/factoid.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/__pycache__/factoid.cpython-38.pyc -------------------------------------------------------------------------------- /tasks/__pycache__/factoid.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/__pycache__/factoid.cpython-39.pyc -------------------------------------------------------------------------------- /tasks/__pycache__/longform.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/__pycache__/longform.cpython-39.pyc -------------------------------------------------------------------------------- /tasks/__pycache__/multichoice.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/__pycache__/multichoice.cpython-39.pyc -------------------------------------------------------------------------------- /tasks/__pycache__/openbook.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/__pycache__/openbook.cpython-39.pyc -------------------------------------------------------------------------------- /tasks/__pycache__/opendomain.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/__pycache__/opendomain.cpython-39.pyc -------------------------------------------------------------------------------- /tasks/closedbook.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/closedbook.py -------------------------------------------------------------------------------- /tasks/longform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/longform.py -------------------------------------------------------------------------------- /tasks/multichoice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/multichoice.py -------------------------------------------------------------------------------- /tasks/openbook.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/tasks/openbook.py -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /utils/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /utils/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /utils/__pycache__/cd_diagram.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/__pycache__/cd_diagram.cpython-39.pyc -------------------------------------------------------------------------------- /utils/__pycache__/clustering.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/__pycache__/clustering.cpython-38.pyc -------------------------------------------------------------------------------- /utils/__pycache__/clustering.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/__pycache__/clustering.cpython-39.pyc -------------------------------------------------------------------------------- /utils/__pycache__/make_plots.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/__pycache__/make_plots.cpython-38.pyc -------------------------------------------------------------------------------- /utils/__pycache__/make_plots.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/__pycache__/make_plots.cpython-39.pyc -------------------------------------------------------------------------------- /utils/__pycache__/text_processing.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/__pycache__/text_processing.cpython-38.pyc -------------------------------------------------------------------------------- /utils/__pycache__/text_processing.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/__pycache__/text_processing.cpython-39.pyc -------------------------------------------------------------------------------- /utils/cd_diagram.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/cd_diagram.py -------------------------------------------------------------------------------- /utils/clustering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/clustering.py -------------------------------------------------------------------------------- /utils/make_plots.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/make_plots.py -------------------------------------------------------------------------------- /utils/prompt_engine.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /utils/text_processing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shuoli90/Rank-Calibration/HEAD/utils/text_processing.py --------------------------------------------------------------------------------