arXiv 2504.009932025-04-04cs.CLcs.AI

MedReason：通过知识图谱在LLM中引出事实性医疗推理步骤

MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs

UC Santa Cruz（加州大学圣克鲁兹分校）；University of British Columbia（不列颠哥伦比亚大学）；Nanyang Technological University（南洋理工大学）；Stanford University（斯坦福大学）；Weill Cornell Medicine（威尔康奈尔医学院）；NYU Langone Health（纽约大学兰贡医学中心）；Chungnam National University Sejong Hospital（忠南大学世宗医院）；Vector Institute（矢量研究院）；Pusan National University Hospital（釜山国立大学医院）；Massachusetts General Hospital（麻省总医院）

Juncheng Wu, Wenlong Deng, Xingxuan Li, Sheng Liu, Taomian Mi, Yifan Peng, Ziyang Xu, Yi Liu, Hyunjin Cho, Chang-In Choi, Yihan Cao, Hui Ren, Xiang Li, Xiaoxiao Li, Yuyin Zhou

备注：: 18 pages, 11 figures, 6 tables. Project page: https://github.com/UCSC-VLAA/MedReason

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对医疗推理缺乏透明步骤数据集的问题，提出MedReason数据集，利用知识图谱将临床QA转化为逻辑推理链，微调后显著提升了LLM的医疗问题求解能力并超越现有先进模型。

摘要：

诊断和治疗规划等医疗任务需要精确且复杂的推理，特别是在生命攸关的领域。与数学推理不同，医疗推理要求严谨、可验证的思维过程以确保可靠性和准确性。然而，目前明显缺乏提供透明、逐步推理的数据集，以验证和增强AI模型的医疗推理能力。为了填补这一空白，我们推出了MedReason，这是一个大规模、高质量的医疗推理数据集，旨在实现大型语言模型（LLM）中忠实且可解释的医疗问题求解。我们利用结构化医疗知识图谱（KG），将临床QA对转化为逻辑推理链，即“思维路径”，这些路径通过相关的KG实体追踪从问题元素到答案的连接。每条路径都经过验证，以确保与临床逻辑和循证医学保持一致。我们的处理流程为来自7个医疗数据集的各种医疗问题生成了详细的推理，最终形成了一个包含32,682个问答对的数据集，每个问答对都附有详细的、逐步的解释。实验表明，使用我们的数据集进行微调能持续提升医疗问题求解能力，使DeepSeek-Distill-8B获得了高达7.7%的显著提升。我们表现最佳的模型MedReason-8B在临床基准MedBullets上，比最先进的医疗推理模型Huatuo-o1-8B高出达4.2%。我们还邀请了来自不同专科的医疗专业人员来评估我们数据集的质量，确保MedReason提供准确且连贯的医疗推理。我们的数据、模型和代码可在https://github.com/UCSC-VLAA/MedReason获取。

英文摘要：

Medical tasks such as diagnosis and treatment planning require precise and complex reasoning, particularly in life-critical domains. Unlike mathematical reasoning, medical reasoning demands meticulous, verifiable thought processes to ensure reliability and accuracy. However, there is a notable lack of datasets that provide transparent, step-by-step reasoning to validate and enhance the medical reasoning ability of AI models. To bridge this gap, we introduce MedReason, a large-scale high-quality medical reasoning dataset designed to enable faithful and explainable medical problem-solving in large language models (LLMs). We utilize a structured medical knowledge graph (KG) to convert clinical QA pairs into logical chains of reasoning, or ``thinking paths'', which trace connections from question elements to answers via relevant KG entities. Each path is validated for consistency with clinical logic and evidence-based medicine. Our pipeline generates detailed reasoning for various medical questions from 7 medical datasets, resulting in a dataset of 32,682 question-answer pairs, each with detailed, step-by-step explanations. Experiments demonstrate that fine-tuning with our dataset consistently boosts medical problem-solving capabilities, achieving significant gains of up to 7.7% for DeepSeek-Ditill-8B. Our top-performing model, MedReason-8B, outperforms the Huatuo-o1-8B, a state-of-the-art medical reasoning model, by up to 4.2% on the clinical benchmark MedBullets. We also engage medical professionals from diverse specialties to assess our dataset's quality, ensuring MedReason offers accurate and coherent medical reasoning. Our data, models, and code is available at https://github.com/UCSC-VLAA/MedReason.

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。