健康发展与政策研究2025，Vol.28Issue(1)：65-72,79,9.DOI:10.12458/HDPR.202407099
医疗大语言模型的评价现状及思考
Current status and considerations for evaluating medical large language models
摘要
Abstract
Medical large language models(LLMs)are expected to improve the efficiency and quality of modern medical services by offering new tools.Robust and rational evaluation methodologies are essential to support scientific medical decision-making.Although the development of the domestic medical LLMs has closely follows the international advancements,research and practical experience in their evaluation method remains limited.This study reviews the current progress of the LLMs'evaluation tools,summarizes the evaluation approaches,and analyzes key difficulties,aiming to provide a foundation for improving the evaluation framework.关键词
大语言模型/医疗保健/评价Key words
large language model/healthcare/evaluation分类
预防医学引用本文复制引用
邢倩,何达..医疗大语言模型的评价现状及思考[J].健康发展与政策研究,2025,28(1):65-72,79,9.基金项目
上海市加强公共卫生体系建设三年行动计划(2023-2025年)重点学科建设项目——健康教育与健康促进(GWVI-11.1-44) （2023-2025年）
