MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Mianxin, Ding, Jinru, Xu, Jie, Hu, Weiguo, Li, Xiaoyang, Zhu, Lifeng, Bai, Zhian, Shi, Xiaoming, Wang, Benyou, Song, Haitao, Liu, Pengfei, Zhang, Xiaofan, Wang, Shanshan, Li, Kang, Wang, Haofen, Ruan, Tong, Huang, Xuanjing, Sun, Xin, Zhang, Shaoting
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917722738130944
author Liu, Mianxin
Ding, Jinru
Xu, Jie
Hu, Weiguo
Li, Xiaoyang
Zhu, Lifeng
Bai, Zhian
Shi, Xiaoming
Wang, Benyou
Song, Haitao
Liu, Pengfei
Zhang, Xiaofan
Wang, Shanshan
Li, Kang
Wang, Haofen
Ruan, Tong
Huang, Xuanjing
Sun, Xin
Zhang, Shaoting
author_facet Liu, Mianxin
Ding, Jinru
Xu, Jie
Hu, Weiguo
Li, Xiaoyang
Zhu, Lifeng
Bai, Zhian
Shi, Xiaoming
Wang, Benyou
Song, Haitao
Liu, Pengfei
Zhang, Xiaofan
Wang, Shanshan
Li, Kang
Wang, Haofen
Ruan, Tong
Huang, Xuanjing
Sun, Xin
Zhang, Shaoting
contents Ensuring the general efficacy and goodness for human beings from medical large language models (LLM) before real-world deployment is crucial. However, a widely accepted and accessible evaluation process for medical LLM, especially in the Chinese context, remains to be established. In this work, we introduce "MedBench", a comprehensive, standardized, and reliable benchmarking system for Chinese medical LLM. First, MedBench assembles the currently largest evaluation dataset (300,901 questions) to cover 43 clinical specialties and performs multi-facet evaluation on medical LLM. Second, MedBench provides a standardized and fully automatic cloud-based evaluation infrastructure, with physical separations for question and ground truth. Third, MedBench implements dynamic evaluation mechanisms to prevent shortcut learning and answer remembering. Applying MedBench to popular general and medical LLMs, we observe unbiased, reproducible evaluation results largely aligning with medical professionals' perspectives. This study establishes a significant foundation for preparing the practical applications of Chinese medical LLMs. MedBench is publicly accessible at https://medbench.opencompass.org.cn.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10990
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models
Liu, Mianxin
Ding, Jinru
Xu, Jie
Hu, Weiguo
Li, Xiaoyang
Zhu, Lifeng
Bai, Zhian
Shi, Xiaoming
Wang, Benyou
Song, Haitao
Liu, Pengfei
Zhang, Xiaofan
Wang, Shanshan
Li, Kang
Wang, Haofen
Ruan, Tong
Huang, Xuanjing
Sun, Xin
Zhang, Shaoting
Computation and Language
Artificial Intelligence
Ensuring the general efficacy and goodness for human beings from medical large language models (LLM) before real-world deployment is crucial. However, a widely accepted and accessible evaluation process for medical LLM, especially in the Chinese context, remains to be established. In this work, we introduce "MedBench", a comprehensive, standardized, and reliable benchmarking system for Chinese medical LLM. First, MedBench assembles the currently largest evaluation dataset (300,901 questions) to cover 43 clinical specialties and performs multi-facet evaluation on medical LLM. Second, MedBench provides a standardized and fully automatic cloud-based evaluation infrastructure, with physical separations for question and ground truth. Third, MedBench implements dynamic evaluation mechanisms to prevent shortcut learning and answer remembering. Applying MedBench to popular general and medical LLMs, we observe unbiased, reproducible evaluation results largely aligning with medical professionals' perspectives. This study establishes a significant foundation for preparing the practical applications of Chinese medical LLMs. MedBench is publicly accessible at https://medbench.opencompass.org.cn.
title MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.10990