数字中医药（英文）2025，Vol.8Issue(1)：36-45,10.DOI:10.1016/j.dcmed.2025.03.011
TCMLCM:基于KG2TRAG方法的中医肺癌智能问答模型
TCMLCM:an intelligent question-answering model for traditional Chinese medicine lung cancer based on the KG2TRAG method
摘要
Abstract
Objective To improve the accuracy and professionalism of question-answering(QA)model in traditional Chinese medicine(TCM)lung cancer by integrating large language models with structured knowledge graphs using the knowledge graph(KG)to text-enhanced retrieval-augmented generation(KG2TRAG)method. Methods The TCM lung cancer model(TCMLCM)was constructed by fine-tuning Chat-GLM2-6B on the specialized datasets Tianchi TCM,HuangDi,and ShenNong-TCM-Dataset,as well as a TCM lung cancer KG.The KG2TRAG method was applied to enhance the knowl-edge retrieval,which can convert KG triples into natural language text via ChatGPT-aided lin-earization,leveraging large language models(LLMs)for context-aware reasoning.For a com-prehensive comparison,MedicalGPT,HuatuoGPT,and BenTsao were selected as the base-line models.Performance was evaluated using bilingual evaluation understudy(BLEU),re-call-oriented understudy for gisting evaluation(ROUGE),accuracy,and the domain-specific TCM-LCEval metrics,with validation from TCM oncology experts assessing answer accuracy,professionalism,and usability. Results The TCMLCM model achieved the optimal performance across all metrics,including a BLEU score of 32.15%,ROUGE-L of 59.08%,and an accuracy rate of 79.68%.Notably,in the TCM-LCEval assessment specific to the field of TCM,its performance was 3%-12%higher than that of the baseline model.Expert evaluations highlighted superior performance in accu-racy and professionalism. Conclusion TCMLCM can provide an innovative solution for TCM lung cancer QA,demon-strating the feasibility of integrating structured KGs with LLMs.This work advances intelli-gent TCM healthcare tools and lays a foundation for future AI-driven applications in tradi-tional medicine.关键词
中医/肺癌/问答/大语言模型/微调/知识图谱/KG2TRAG方法Key words
Traditional Chinese medicine(TCM)/Lung cancer/Question-answering/Large language model/Fine-tuning/Knowledge graph/KG2TRAG method引用本文复制引用
周春芳,龚庆悦,詹文栋,朱金阳,栾慧丹..TCMLCM:基于KG2TRAG方法的中医肺癌智能问答模型[J].数字中医药（英文）,2025,8(1):36-45,10.基金项目
Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX24_2145). （KYCX24_2145）
