摘要
目的 利用Langchain框架与大模型相结合并搭载知识库创建一个问答系统,为大模型在医学知识问答领域的应用作出技术探索。方法 引入由中华中医药学会、中华医学会等权威机构认证的阿尔茨海默病(Alzheimer’s disease,AD)诊疗指南和诊疗规范的知识文件以及医学教科书,构建AD本地知识库。通过知识库增强模型在AD知识问答方面的能力,最终实现ChatGLM3-6B模型在AD医学问答方面的应用。结果 使用响应事实准确性(FA)和响应完整性(CR)作为评估指标,AD问答系统与ChatGLM3-6B、ChatGPT大模型进行对比实验,表现更优的标记为Win,表现持平则为Tie。AD问答系统与ChatGLM3-6B模型进行对比,在FA上AD问答系统Win值88.09%,Tie值7.14%;在CR上AD问答系统Win值85.71%,Tie值11.90%。与ChatGPT模型进行对比,在FA上AD问答系统Win值54.76%,Tie值30.95%;在CR上AD问答系统Win值35.71%,Tie值40.47%。结论 AD问答系统相比ChatGLM3-6B和ChatGPT模型在FA和CR的表现更好,证实了本研究方法的有效性。
Objective Utilizing the Langchain framework in combination with large models and integrating a knowledge base to create a question-answering system,this paper conducts a technical exploration of the application of large models in the field of medical knowledge question and answer.Methods Authenticated knowledge documents,including diagnostic and treatment guidelines for AD endorsed by authoritative organizations such as the Chinese Association of Integrative Medicine and the Chinese Medical Association,along with medical textbooks,were introduced to construct a local knowledge base for AD.This knowledge base enhanced the model’s capability in AD-related question-answering.Ultimately,the application of the ChatGLM3-6B model in AD medical question-answering was achieved.Results Using Fact accuracy(FA)and Completeness of response(CR)as evaluation metrics,comparative experiments were conducted between the AD question-answering system and the ChatGLM3-6B and ChatGPT large models.Superior performance is denoted as Win,while equal performance is denoted as Tie.Comparing with the ChatGLM3-6B model,the AD question-answering system achieved a Win rate of 88.09%in FA and a Tie rate of 7.14%,and a Win rate of 85.71%in CR with a Tie rate of 11.90%.Compared to the ChatGPT model,the AD questionanswering system attained a Win rate of 54.76%in FA with a Tie rate of 30.95%and a Win rate of 35.71%in CR with a Tie rate of 40.47%.Conclusion The AD question-answering system demonstrated better performance in FA and CR compared to the ChatGLM3-6B and ChatGPT models,confirming the effectiveness of the approach proposed in this study.
作者
王文湖
韦昌法
WANG Wenhu;WEI Changfa(School of Informatics,Hunan University of Chinese Medicine,Changsha 410208,China)
出处
《世界科学技术-中医药现代化》
北大核心
2025年第3期856-866,共11页
Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology
基金
湖南省教育厅科学研究项目(23A0312):中医情志数字化表征与计算研究,负责人:晏峻峰
湖南中医药大学信息科学与工程学院科研资助专项(DK2023KY05):基于大语言模型的脑卒中诊疗知识智能问答系统构建关键技术研究,负责人:韦昌法
湖南中医药大学研究生创新项目(2024CX194):基于大模型与医学知识的视觉问答多跳推理方法研究,负责人:王文湖。
关键词
大语言模型
检索增强生成
本地知识库
阿尔茨海默病
问答系统
Large language model
Retrieval-augmented generation
Local knowledge base
Alzheimer’s disease
Question-answering system
