广西医科大学学报2025，Vol.42Issue(3)：323-331,9.DOI:10.16190/j.cnki.45-1211/r.2025.03.001
大语言模型辅助医学系统综述:方法、发展方向和应用
Empowering medical systematic reviews with large language models:methods,development directions,and applications
摘要
Abstract
With the exponential growth of biomedical literature,traditional keyword-based retrieval methods are increasingly inadequate for meeting the dual demands of efficiency and precision in clinical and research con-texts.In recent years,large language models(LLMs),exemplified by ChatGPT and DeepSeek,have demon-strated significant potential in supporting medical systematic reviews due to their powerful natural language pro-cessing capabilities.However,its inherent challenges such as the"hallucination"problem and lagging knowledge update limit the reliability of its direct application.This paper systematically introduces six core technical ap-proaches currently used to mitigate hallucinations in LLMs,with a particular focus on explaining the principles and application advantages of retrieval-augmented generation(RAG).After comprehensively reviewing the tech-nical characteristics and application scenarios of 22 representative studies in the context of systematic reviews,the paper further identifies LLMs capable of"structured understanding and generation based on levels of evi-dence"as one of the key future directions.The goal is to provide systematic guidance for medical researchers and clinical practitioners,helping them make scientific and efficient use of LLMs to enhance the efficiency of bio-medical literature processing and the quality of evidence-based medical decision-making.关键词
大语言模型/医学系统综述/检索增强生成/提示工程Key words
large language models/medical systematic reviews/retrieval-augmented generation/prompt engi-neering分类
社会科学引用本文复制引用
黄衍楠,桑浩然,刘宇,马连韬,朱英豪..大语言模型辅助医学系统综述:方法、发展方向和应用[J].广西医科大学学报,2025,42(3):323-331,9.基金项目
国家自然科学基金资助项目(No.62402017) （No.62402017）
