├── README.md ├── data ├── CheckupQA.jsonl ├── EMRHG.jsonl ├── MedQA-USMLE.jsonl ├── MedQA_Mainland.jsonl ├── MedTreat.jsonl ├── MedTriage.jsonl ├── MedicineQA_RAG.jsonl ├── PromptCBLUE.jsonl └── webMedQA.jsonl ├── environment.yaml ├── eval ├── elo │ ├── elo_data │ │ ├── CheckupQA_1207.jsonl │ │ ├── DialogSumm_1207.jsonl │ │ ├── MedQA-Mainland_1207.jsonl │ │ ├── MedQA-USMLE_1207.jsonl │ │ ├── MedTriage_1207.jsonl │ │ ├── MedicineQA_1207.jsonl │ │ ├── PromptCBLUE_1207.jsonl │ │ └── WebMedQA_1207.jsonl │ ├── elo_inputs │ │ ├── CheckupQA_1207.jsonl │ │ ├── DialogSumm_1207.jsonl │ │ ├── MedQA-Mainland_1207.jsonl │ │ ├── MedQA-USMLE_1207.jsonl │ │ ├── MedTriage_1207.jsonl │ │ ├── MedicineQA_1207.jsonl │ │ ├── PromptCBLUE_1207.jsonl │ │ └── WebMedQA_1207.jsonl │ └── elo_outputs │ │ ├── CheckupQA_1207.jsonl │ │ ├── DialogSumm_1207.jsonl │ │ ├── MedQA-Mainland_1207.jsonl │ │ ├── MedQA-USMLE_1207.jsonl │ │ ├── MedTriage_1207.jsonl │ │ ├── MedicineQA_1207.jsonl │ │ ├── PromptCBLUE_1207.jsonl │ │ └── WebMedQA_1207.jsonl ├── elo_analysis.py ├── elo_utils.py ├── eval_utils.py ├── main.py └── predicted │ ├── Baichuan2 │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ └── WebMedQA.jsonl │ ├── BenTsao │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ └── WebMedQA.jsonl │ ├── BianQue2 │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ └── WebMedQA.jsonl │ ├── ChatGLM3 │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ └── WebMedQA.jsonl │ ├── ChatGPT │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ └── WebMedQA.jsonl │ ├── DoctorGLM │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ ├── WebMedQA.jsonl │ └── test.ipynb │ ├── GPT-4 │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ └── WebMedQA.jsonl │ ├── HuatuoGPT2 │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ └── WebMedQA.jsonl │ ├── MING │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ └── WebMedQA.jsonl │ ├── PULSE-OS │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ ├── WebMedQA.jsonl │ └── deepspeed.json │ ├── PULSE-Pro │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ └── WebMedQA.jsonl │ └── QiZhenGPT │ ├── CheckupQA.jsonl │ ├── DialogSumm.jsonl │ ├── MedQA-Mainland.jsonl │ ├── MedQA-USMLE.jsonl │ ├── MedTriage.jsonl │ ├── MedicineQA.jsonl │ ├── PromptCBLUE.jsonl │ └── WebMedQA.jsonl ├── rank_table.md ├── requirements.txt └── score_table.md /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/README.md -------------------------------------------------------------------------------- /data/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/data/CheckupQA.jsonl -------------------------------------------------------------------------------- /data/EMRHG.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/data/EMRHG.jsonl -------------------------------------------------------------------------------- /data/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/data/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /data/MedQA_Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/data/MedQA_Mainland.jsonl -------------------------------------------------------------------------------- /data/MedTreat.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/data/MedTreat.jsonl -------------------------------------------------------------------------------- /data/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/data/MedTriage.jsonl -------------------------------------------------------------------------------- /data/MedicineQA_RAG.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/data/MedicineQA_RAG.jsonl -------------------------------------------------------------------------------- /data/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/data/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /data/webMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/data/webMedQA.jsonl -------------------------------------------------------------------------------- /environment.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/environment.yaml -------------------------------------------------------------------------------- /eval/elo/elo_data/CheckupQA_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_data/CheckupQA_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_data/DialogSumm_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_data/DialogSumm_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_data/MedQA-Mainland_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_data/MedQA-Mainland_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_data/MedQA-USMLE_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_data/MedQA-USMLE_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_data/MedTriage_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_data/MedTriage_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_data/MedicineQA_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_data/MedicineQA_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_data/PromptCBLUE_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_data/PromptCBLUE_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_data/WebMedQA_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_data/WebMedQA_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_inputs/CheckupQA_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_inputs/CheckupQA_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_inputs/DialogSumm_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_inputs/DialogSumm_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_inputs/MedQA-Mainland_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_inputs/MedQA-Mainland_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_inputs/MedQA-USMLE_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_inputs/MedQA-USMLE_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_inputs/MedTriage_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_inputs/MedTriage_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_inputs/MedicineQA_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_inputs/MedicineQA_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_inputs/PromptCBLUE_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_inputs/PromptCBLUE_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_inputs/WebMedQA_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_inputs/WebMedQA_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_outputs/CheckupQA_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_outputs/CheckupQA_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_outputs/DialogSumm_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_outputs/DialogSumm_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_outputs/MedQA-Mainland_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_outputs/MedQA-Mainland_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_outputs/MedQA-USMLE_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_outputs/MedQA-USMLE_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_outputs/MedTriage_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_outputs/MedTriage_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_outputs/MedicineQA_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_outputs/MedicineQA_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_outputs/PromptCBLUE_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_outputs/PromptCBLUE_1207.jsonl -------------------------------------------------------------------------------- /eval/elo/elo_outputs/WebMedQA_1207.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo/elo_outputs/WebMedQA_1207.jsonl -------------------------------------------------------------------------------- /eval/elo_analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo_analysis.py -------------------------------------------------------------------------------- /eval/elo_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/elo_utils.py -------------------------------------------------------------------------------- /eval/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/eval_utils.py -------------------------------------------------------------------------------- /eval/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/main.py -------------------------------------------------------------------------------- /eval/predicted/Baichuan2/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/Baichuan2/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/Baichuan2/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/Baichuan2/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/Baichuan2/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/Baichuan2/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/Baichuan2/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/Baichuan2/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/Baichuan2/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/Baichuan2/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/Baichuan2/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/Baichuan2/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/Baichuan2/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/Baichuan2/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/Baichuan2/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/Baichuan2/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/BenTsao/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BenTsao/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/BenTsao/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BenTsao/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/BenTsao/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BenTsao/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/BenTsao/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BenTsao/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/BenTsao/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BenTsao/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/BenTsao/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BenTsao/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/BenTsao/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BenTsao/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/BenTsao/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BenTsao/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/BianQue2/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BianQue2/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/BianQue2/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BianQue2/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/BianQue2/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BianQue2/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/BianQue2/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BianQue2/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/BianQue2/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BianQue2/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/BianQue2/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BianQue2/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/BianQue2/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BianQue2/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/BianQue2/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/BianQue2/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGLM3/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGLM3/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGLM3/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGLM3/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGLM3/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGLM3/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGLM3/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGLM3/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGLM3/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGLM3/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGLM3/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGLM3/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGLM3/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGLM3/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGLM3/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGLM3/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGPT/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGPT/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGPT/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGPT/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGPT/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGPT/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGPT/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGPT/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGPT/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGPT/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGPT/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGPT/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGPT/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGPT/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/ChatGPT/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/ChatGPT/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/DoctorGLM/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/DoctorGLM/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/DoctorGLM/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/DoctorGLM/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/DoctorGLM/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/DoctorGLM/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/DoctorGLM/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/DoctorGLM/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/DoctorGLM/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/DoctorGLM/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/DoctorGLM/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/DoctorGLM/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/DoctorGLM/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/DoctorGLM/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/DoctorGLM/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/DoctorGLM/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/DoctorGLM/test.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/DoctorGLM/test.ipynb -------------------------------------------------------------------------------- /eval/predicted/GPT-4/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/GPT-4/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/GPT-4/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/GPT-4/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/GPT-4/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/GPT-4/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/GPT-4/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/GPT-4/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/GPT-4/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/GPT-4/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/GPT-4/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/GPT-4/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/GPT-4/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/GPT-4/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/GPT-4/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/GPT-4/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/HuatuoGPT2/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/HuatuoGPT2/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/HuatuoGPT2/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/HuatuoGPT2/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/HuatuoGPT2/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/HuatuoGPT2/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/HuatuoGPT2/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/HuatuoGPT2/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/HuatuoGPT2/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/HuatuoGPT2/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/HuatuoGPT2/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/HuatuoGPT2/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/HuatuoGPT2/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/HuatuoGPT2/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/HuatuoGPT2/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/HuatuoGPT2/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/MING/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/MING/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/MING/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/MING/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/MING/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/MING/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/MING/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/MING/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/MING/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/MING/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/MING/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/MING/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/MING/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/MING/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/MING/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/MING/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-OS/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-OS/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-OS/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-OS/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-OS/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-OS/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-OS/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-OS/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-OS/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-OS/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-OS/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-OS/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-OS/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-OS/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-OS/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-OS/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-OS/deepspeed.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-OS/deepspeed.json -------------------------------------------------------------------------------- /eval/predicted/PULSE-Pro/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-Pro/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-Pro/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-Pro/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-Pro/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-Pro/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-Pro/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-Pro/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-Pro/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-Pro/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-Pro/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-Pro/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-Pro/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-Pro/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/PULSE-Pro/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/PULSE-Pro/WebMedQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/QiZhenGPT/CheckupQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/QiZhenGPT/CheckupQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/QiZhenGPT/DialogSumm.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/QiZhenGPT/DialogSumm.jsonl -------------------------------------------------------------------------------- /eval/predicted/QiZhenGPT/MedQA-Mainland.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/QiZhenGPT/MedQA-Mainland.jsonl -------------------------------------------------------------------------------- /eval/predicted/QiZhenGPT/MedQA-USMLE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/QiZhenGPT/MedQA-USMLE.jsonl -------------------------------------------------------------------------------- /eval/predicted/QiZhenGPT/MedTriage.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/QiZhenGPT/MedTriage.jsonl -------------------------------------------------------------------------------- /eval/predicted/QiZhenGPT/MedicineQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/QiZhenGPT/MedicineQA.jsonl -------------------------------------------------------------------------------- /eval/predicted/QiZhenGPT/PromptCBLUE.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/QiZhenGPT/PromptCBLUE.jsonl -------------------------------------------------------------------------------- /eval/predicted/QiZhenGPT/WebMedQA.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/eval/predicted/QiZhenGPT/WebMedQA.jsonl -------------------------------------------------------------------------------- /rank_table.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/rank_table.md -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/requirements.txt -------------------------------------------------------------------------------- /score_table.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/openmedlab/PULSE-EVAL/HEAD/score_table.md --------------------------------------------------------------------------------