世界科学技术-中医药现代化2025，Vol.27Issue(7)：1898-1905,8.DOI:10.11842/wst.20241121002
融合监督微调和检索增强的中医知识问答模型研究
Research on a Traditional Chinese Medicine Knowledge Q&A Model Integrating Supervised Fine-Tuning and Retrieval-Augmented Generation
摘要
Abstract
Objective To construct a traditional Chinese medicine(TCM)knowledge question-answering model with strong reasoning capabilities and reliable results,TCM Q&A datasets and TCM literature were fully utilized.Methods Large-scale TCM corpus and Q&A data were collected and organized,with ChatGLM3 serving as the base model.The PissA method was used for supervised fine-tuning,combined with retrieval-augmented generation(RAG)techniques,to build a TCM knowledge Q&A model that integrates supervised fine-tuning and retrieval-augmented generation.The model was compared with ChatGLM3,SFT,and RAG,with evaluations based on classic metrics such as BLEU,ROUGE1,and F-scores.Results The model in this paper achieved BLEU and ROUGE1 scores of 14.5830 and 34.6730,respectively.After incorporating retrieval-augmented generation,the model attained an F score of 0.6398 in the inference results on a TCM dataset,outperforming the ChatGLM3 baseline model's 0.2654.Conclusion The construction method of a large model in the TCM domain that integrates supervised fine-tuning and retrieval augmentation can effectively enhance the model's reasoning performance and reliability in TCM.关键词
监督微调/检索增强生成/大语言模型/中医知识问答Key words
Supervised fine-tuning/Retrieval-augmented generation/Large language model/TCM knowledge question answering分类
医药卫生引用本文复制引用
王欣宇,杨涛,王松,徐忆初,胡孔法..融合监督微调和检索增强的中医知识问答模型研究[J].世界科学技术-中医药现代化,2025,27(7):1898-1905,8.基金项目
国家自然科学基金委员会面上项目(82174276):知识和数据协同驱动的中医藏象智能辨证方法研究——以心系疾病为例,负责人:杨涛 （82174276）
江苏省中医流派研究院开放课题(JSZYLP2024060):基于大模型技术的江苏中医流派知识挖掘和服务创新方法学研究,负责人:杨涛. （JSZYLP2024060）
