arXiv 2509.058672025-09-06cs.CLcs.AI

ZhiFangDanTai：面向中药方剂的基于图的检索增强生成模型微调

ZhiFangDanTai: Fine-tuning Graph-based Retrieval-Augmented Generation Model for Traditional Chinese Medicine Formula

School of Management, Capital Normal University（管理学院，首都师范大学）；School of Electrical Engineering and Computer Science, the University of Queensland（电气工程与计算机科学学院，昆士兰大学）

ZiXuan Zhang, Bowen Hao, Yingjie Li, Hongzhi Yin

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对中药方剂生成中数据细节不足和模型输出深度有限的问题，提出ZhiFangDanTai框架，结合GraphRAG与LLM微调，并理论证明可降低泛化误差和幻觉率，实验显示优于现有模型。

摘要：

中药方剂在治疗流行病和复杂疾病中发挥着重要作用。现有的中药模型利用传统算法或深度学习技术分析方剂关系，但缺乏全面的结果，如完整的方剂组成和详细解释。尽管最近的工作使用中药指令数据集微调大型语言模型（LLMs）以生成可解释的方剂，但现有数据集缺乏足够的细节，如方剂中君、臣、佐、使的角色；功效；禁忌；舌脉诊断——限制了模型输出的深度。为解决这些挑战，我们提出了ZhiFangDanTai，一个结合基于图的检索增强生成（GraphRAG）与LLM微调的框架。ZhiFangDanTai使用GraphRAG检索并综合结构化的中药知识为简洁摘要，同时构建增强的指令数据集以提升LLM整合检索信息的能力。此外，我们提供了新颖的理论证明，表明将GraphRAG与微调技术结合可以减少中药方剂任务中的泛化误差和幻觉率。在收集的数据集和临床数据集上的实验结果表明，ZhiFangDanTai相较于最先进的模型取得了显著改进。我们的模型已在https://huggingface.co/tczzx6/ZhiFangDanTai1.0开源。

英文摘要：

Traditional Chinese Medicine (TCM) formulas play a significant role in treating epidemics and complex diseases. Existing models for TCM utilize traditional algorithms or deep learning techniques to analyze formula relationships, yet lack comprehensive results, such as complete formula compositions and detailed explanations. Although recent efforts have used TCM instruction datasets to fine-tune Large Language Models (LLMs) for explainable formula generation, existing datasets lack sufficient details, such as the roles of the formula's sovereign, minister, assistant, courier; efficacy; contraindications; tongue and pulse diagnosis-limiting the depth of model outputs. To address these challenges, we propose ZhiFangDanTai, a framework combining Graph-based Retrieval-Augmented Generation (GraphRAG) with LLM fine-tuning. ZhiFangDanTai uses GraphRAG to retrieve and synthesize structured TCM knowledge into concise summaries, while also constructing an enhanced instruction dataset to improve LLMs' ability to integrate retrieved information. Furthermore, we provide novel theoretical proofs demonstrating that integrating GraphRAG with fine-tuning techniques can reduce generalization error and hallucination rates in the TCM formula task. Experimental results on both collected and clinical datasets demonstrate that ZhiFangDanTai achieves significant improvements over state-of-the-art models. Our model is open-sourced at https://huggingface.co/tczzx6/ZhiFangDanTai1.0.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。