Research Article
Chinese Medicine Question Answering Robot Based on RAG and Self-Built Dataset
@INPROCEEDINGS{10.4108/eai.21-11-2024.2354617, author={Enpu Zuo and Chenxi Pan and Junyu Chen and Zihan Yi}, title={Chinese Medicine Question Answering Robot Based on RAG and Self-Built Dataset}, proceedings={Proceedings of the 2nd International Conference on Machine Learning and Automation, CONF-MLA 2024, November 21, 2024, Adana, Turkey}, publisher={EAI}, proceedings_a={CONF-MLA}, year={2025}, month={3}, keywords={traditional chinese medicine (tcm) large language models (llms) retrieval-augmented generation (rag) question \& answer robot(q\&a robot)}, doi={10.4108/eai.21-11-2024.2354617} }- Enpu Zuo
Chenxi Pan
Junyu Chen
Zihan Yi
Year: 2025
Chinese Medicine Question Answering Robot Based on RAG and Self-Built Dataset
CONF-MLA
EAI
DOI: 10.4108/eai.21-11-2024.2354617
Abstract
Traditional Chinese Medicine (TCM) is a cornerstone of China's medical heritage, renowned for its unique methods of diagnosis and treatment. Despite its long history, TCM faces challenges in the modernization process due to its reliance on doctors' expertise and lack of systematic knowledge integration. This paper introduces two major innovations: the development of the most comprehensive Chinese medicine database and the first application of search-enhanced generation Retrieval-Augmented Generation(RAG) technology. In this paper, the most comprehensive TCM database was established by crawler and OCR, and the model's understanding of TCM knowledge was enhanced through the integration of Large language models(LLMs) and RAG technology, and the ability to systematically retrieve relevant prescriptions and literature was realized to achieve more personalized and accurate treatment recommendations. We tested it on a test set and invited TCM experts to evaluate it, which validated the accuracy and reliability of our model.
