mlsanityData to 7 Oct 2026

TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought

arXiv 2602.22828 ↗First posted 26 Feb 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Clinical and biomedical applications

also in 1 more
Abstract (arXiv)

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 native LLMs. For example, the qwen-plus model achieved scores of 0.927, 0.361, and 0.038, which were significantly enhanced to 0.952, 0.788, and 0.356 with TCM-DiffRAG. The improvements were even more pronounced for non-Chinese LLMs. Additionally, TCM-DiffRAG outperformed directly supervised fine-tuned (SFT) LLMs and other benchmark RAG methods. Conclusions: TCM-DiffRAG shows that integrating structured TCM knowledge graphs with Chain of Thought based reasoning substantially improves performance in individualized diagnostic tasks. The joint use of universal and personalized knowledge graphs enables effective alignment between general knowledge and clinical reasoning. These results highlight the potential of reasoning-aware RAG frameworks for advancing LLM applications in traditional Chinese medicine.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 45 of its 89 references that are in the map. First posted on arXiv 26 Feb 2026.

Builds on

45 of 89 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs1 Apr
  2. 2024Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models25 Aug
  3. 2024Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models27 Jan

Other references · 42

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  3. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  4. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  5. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  6. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  7. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  8. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  9. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  10. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 326
  11. 2023ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledgecited by 324
  12. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningcited by 322
30 more
  1. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 255
  2. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 242
  3. 2023Nougat: Neural Optical Understanding for Academic Documentscited by 240
  4. 2023HuatuoGPT, towards Taming Language Model to Be a Doctorcited by 211
  5. 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agentscited by 210
  6. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learningcited by 152
  7. 2023Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialoguecited by 118
  8. 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understandingcited by 94
  9. 2024Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Modelscited by 91
  10. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  11. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 78
  12. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  13. 2023BianQue: Balancing the Questioning and Suggestion Ability of Health LLMs with Multi-turn Health Conversations Polished by ChatGPTcited by 64
  14. 2021LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysiscited by 58
  15. 2024Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questionscited by 54
  16. 2024In-Context Principle Learning from Mistakescited by 42
  17. 2025DeepRAG: Thinking to Retrieve Step by Step for Large Language Modelscited by 37
  18. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
  19. 2023Guideline Learning for In-context Information Extractioncited by 24
  20. 2023Qilin-Med: Multi-stage Knowledge Injection Advanced Medical Large Language Modelcited by 24
  21. 2023Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinesecited by 18
  22. 2023Learning by Self-Explainingcited by 17
  23. 2024Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUTcited by 14
  24. 2024Qibo: A Large Language Model for Traditional Chinese Medicinecited by 12
  25. 2025OpenTCM: A GraphRAG-Empowered LLM-based System for Traditional Chinese Medicine Knowledge Retrieval and Diagnosiscited by 10
  26. 2025Tree-based RAG-Agent Recommendation System: A Case Study in Medical Test Datacited by 9
  27. 2025Medical large language models are easily distractedcited by 9
  28. 2022TCM-SD: A Benchmark for Probing Syndrome Differentiation via Natural Language Processingcited by 6
  29. 2024Retrieved In-Context Principles from Previous Mistakescited by 5
  30. 2025ZhiFangDanTai: Fine-tuning Graph-based Retrieval-Augmented Generation Model for Traditional Chinese Medicine Formulacited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A benchmark dataset for evaluating Syndrome Differentiation and Treatment in large language models
  2. 2025TCM-Eval: An Expert-Level Dynamic and Extensible Benchmark for Traditional Chinese Medicine
  3. 2025MTCMB: A Multi-Task Benchmark Framework for Evaluating LLMs on Knowledge, Reasoning, and Safety in Traditional Chinese Medicine
  4. 2025The Multi-Round Diagnostic RAG Framework for Emulating Clinical Reasoning
  5. 2026LingLanMiDian: Systematic Evaluation of LLMs on TCM Knowledge and Clinical Reasoning
  6. 2025TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine
  7. 2025Improving TCM Question Answering through Tree-Organized Self-Reflective Retrieval with LLMs
  8. 2025BenCao: An Instruction-Tuned Large Language Model for Traditional Chinese Medicine