![[2602.22828] TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.22828] TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought
Summary
The article presents TCM-DiffRAG, a novel reasoning framework for Traditional Chinese Medicine (TCM) that enhances diagnosis through knowledge graphs and chain of thought methodologies.
Why It Matters
This research addresses the limitations of existing retrieval augmented generation (RAG) methods in TCM, showcasing how tailored frameworks can improve diagnostic accuracy and personalized treatment, which is crucial for advancing AI applications in healthcare.
Key Takeaways
- TCM-DiffRAG integrates knowledge graphs with chain of thought reasoning for improved TCM diagnosis.
- The framework significantly outperformed traditional LLMs and fine-tuned models in TCM applications.
- Results indicate enhanced performance for non-Chinese LLMs, emphasizing its broader applicability.
- The research highlights the importance of personalized knowledge in clinical reasoning.
- This approach could set a precedent for future AI developments in specialized medical fields.
Computer Science > Computation and Language arXiv:2602.22828 (cs) [Submitted on 26 Feb 2026] Title:TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought Authors:Jianmin Li, Ying Chang, Su-Kit Tang, Yujia Liu, Yanwen Wang, Shuyuan Lin, Binkai Ou View a PDF of the paper titled TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought, by Jianmin Li and 6 other authors View PDF Abstract:Background: Retrieval augmented generation (RAG) technology can empower large language models (LLMs) to generate more accurate, professional, and timely responses without fine tuning. However, due to the complex reasoning processes and substantial individual differences involved in traditional Chinese medicine (TCM) clinical diagnosis and treatment, traditional RAG methods often exhibit poor performance in this domain. Objective: To address the limitations of conventional RAG approaches in TCM applications, this study aims to develop an improved RAG framework tailored to the characteristics of TCM reasoning. Methods: We developed TCM-DiffRAG, an innovative RAG framework that integrates knowledge graphs (KG) with chains of thought (CoT). TCM-DiffRAG was evaluated on three distinctive TCM test datasets. Results: The experimental results demonstrated that TCM-DiffRAG achieved significant performance improvements over ...
