├── .gitignore ├── README.md ├── evaluation.py ├── figures └── overview.png ├── requirements.txt ├── retriever ├── get_top_n.py ├── recall_evaluation.py ├── retriever.py ├── src │ └── index.py └── utils │ └── bm25_utils.py ├── run_llm.py ├── scripts ├── evaluation │ ├── evaluate_all.sh │ ├── evaluate_rag_analysis.sh │ └── evaluate_retriever_recall.sh └── inference │ ├── run_api.sh │ ├── run_api_complong_longcontext.sh │ ├── run_rag_analysis.sh │ ├── run_retriever.sh │ ├── run_vllm.sh │ └── run_vllm_complong_longcontext.sh └── utils ├── evaluation_utils.py ├── model_input_utils.py └── openai_utils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/README.md -------------------------------------------------------------------------------- /evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/evaluation.py -------------------------------------------------------------------------------- /figures/overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/figures/overview.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/requirements.txt -------------------------------------------------------------------------------- /retriever/get_top_n.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/retriever/get_top_n.py -------------------------------------------------------------------------------- /retriever/recall_evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/retriever/recall_evaluation.py -------------------------------------------------------------------------------- /retriever/retriever.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/retriever/retriever.py -------------------------------------------------------------------------------- /retriever/src/index.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/retriever/src/index.py -------------------------------------------------------------------------------- /retriever/utils/bm25_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/retriever/utils/bm25_utils.py -------------------------------------------------------------------------------- /run_llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/run_llm.py -------------------------------------------------------------------------------- /scripts/evaluation/evaluate_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/scripts/evaluation/evaluate_all.sh -------------------------------------------------------------------------------- /scripts/evaluation/evaluate_rag_analysis.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/scripts/evaluation/evaluate_rag_analysis.sh -------------------------------------------------------------------------------- /scripts/evaluation/evaluate_retriever_recall.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/scripts/evaluation/evaluate_retriever_recall.sh -------------------------------------------------------------------------------- /scripts/inference/run_api.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/scripts/inference/run_api.sh -------------------------------------------------------------------------------- /scripts/inference/run_api_complong_longcontext.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/scripts/inference/run_api_complong_longcontext.sh -------------------------------------------------------------------------------- /scripts/inference/run_rag_analysis.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/scripts/inference/run_rag_analysis.sh -------------------------------------------------------------------------------- /scripts/inference/run_retriever.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/scripts/inference/run_retriever.sh -------------------------------------------------------------------------------- /scripts/inference/run_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/scripts/inference/run_vllm.sh -------------------------------------------------------------------------------- /scripts/inference/run_vllm_complong_longcontext.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/scripts/inference/run_vllm_complong_longcontext.sh -------------------------------------------------------------------------------- /utils/evaluation_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/utils/evaluation_utils.py -------------------------------------------------------------------------------- /utils/model_input_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/utils/model_input_utils.py -------------------------------------------------------------------------------- /utils/openai_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yale-nlp/DocMath-Eval/HEAD/utils/openai_utils.py --------------------------------------------------------------------------------