├── README.md ├── data ├── fever │ └── fever_dev_all_retrieval_500.json ├── hotpotqa │ └── hotpotqa_dev_all_retrieval_500.json ├── nq │ └── nq_test_all_retrieval_500.json ├── triviaqa │ └── triviaqa_test_all_retrieval_500.json └── wikimultihopqa │ └── wikimultihopqa_dev_all_retrieval_500.json ├── evaluation.py ├── madke.py ├── models ├── __init__.py ├── chatgpt_agent.py ├── gpt4_agent.py └── qwen_agent.py ├── parser.py ├── prompts ├── eval_gpt4_prompt.py ├── fever_prompt.py ├── hotpotqa_prompt.py ├── medmc_prompt.py ├── nq_prompt.py ├── triviaqa_prompt.py └── wikimultihopqa_prompt.py └── utils ├── calculate_tokens.py ├── data_utils.py ├── evaluation_utils.py ├── metrics_calculator.py └── prompt_utils.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/README.md -------------------------------------------------------------------------------- /data/fever/fever_dev_all_retrieval_500.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/data/fever/fever_dev_all_retrieval_500.json -------------------------------------------------------------------------------- /data/hotpotqa/hotpotqa_dev_all_retrieval_500.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/data/hotpotqa/hotpotqa_dev_all_retrieval_500.json -------------------------------------------------------------------------------- /data/nq/nq_test_all_retrieval_500.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/data/nq/nq_test_all_retrieval_500.json -------------------------------------------------------------------------------- /data/triviaqa/triviaqa_test_all_retrieval_500.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/data/triviaqa/triviaqa_test_all_retrieval_500.json -------------------------------------------------------------------------------- /data/wikimultihopqa/wikimultihopqa_dev_all_retrieval_500.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/data/wikimultihopqa/wikimultihopqa_dev_all_retrieval_500.json -------------------------------------------------------------------------------- /evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/evaluation.py -------------------------------------------------------------------------------- /madke.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/madke.py -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /models/chatgpt_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/models/chatgpt_agent.py -------------------------------------------------------------------------------- /models/gpt4_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/models/gpt4_agent.py -------------------------------------------------------------------------------- /models/qwen_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/models/qwen_agent.py -------------------------------------------------------------------------------- /parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/parser.py -------------------------------------------------------------------------------- /prompts/eval_gpt4_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/prompts/eval_gpt4_prompt.py -------------------------------------------------------------------------------- /prompts/fever_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/prompts/fever_prompt.py -------------------------------------------------------------------------------- /prompts/hotpotqa_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/prompts/hotpotqa_prompt.py -------------------------------------------------------------------------------- /prompts/medmc_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/prompts/medmc_prompt.py -------------------------------------------------------------------------------- /prompts/nq_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/prompts/nq_prompt.py -------------------------------------------------------------------------------- /prompts/triviaqa_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/prompts/triviaqa_prompt.py -------------------------------------------------------------------------------- /prompts/wikimultihopqa_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/prompts/wikimultihopqa_prompt.py -------------------------------------------------------------------------------- /utils/calculate_tokens.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/utils/calculate_tokens.py -------------------------------------------------------------------------------- /utils/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/utils/data_utils.py -------------------------------------------------------------------------------- /utils/evaluation_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/utils/evaluation_utils.py -------------------------------------------------------------------------------- /utils/metrics_calculator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/utils/metrics_calculator.py -------------------------------------------------------------------------------- /utils/prompt_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FutureForMe/MADKE/HEAD/utils/prompt_utils.py --------------------------------------------------------------------------------