MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models
This work addresses the need for reliable evaluation of Chinese medical LLMs before real-world deployment, establishing a foundational benchmark for the domain.
The authors tackled the lack of a widely accepted evaluation process for Chinese medical large language models by introducing MedBench, a comprehensive benchmarking system that includes the largest evaluation dataset (300,901 questions) and standardized infrastructure, resulting in unbiased and reproducible results aligning with medical professionals' perspectives.
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.