让医学大模型像医生一样严谨推理，确保每一步都有据可依。
FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning
- 用临床专家设计的评分标准，结合强化学习逐步监督推理过程。
- 在7个医学基准上平均性能提升9%，证据应用质量提高15.5%。
- 适合需要高可信度医疗决策的科研与临床辅助场景。
可信推理在医学中至关重要，临床决策需基于可靠证据并提供透明依据。现有医学大模型或无法主动获取证据，或使用检索结果但缺乏对证据评估与应用过程的监督。为此，我们提出FaithMed框架，将循证医学原则形式化为过程级标准，结合临床专家设计、自动优化的评分体系，采用步骤级过程奖励分配与优势分组的强化学习方法。在七个医学基准测试中，FaithMed平均性能优于代理搜索基线（+9%），也优于仅以结果为导向的强化学习方法（+5.8%），且在循证医学评分标准上较代理搜索基线的Qwen3模型提升15.5%。本研究证明，显式的步骤级监督可同时提升任务成功率与推理过程的可信性。代码已开源：https://github.com/cxcscmu/FaithMed。
原文摘要 · Abstract (English)
Faithful reasoning is essential in medicine, where clinical decisions require transparent justification grounded in reliable evidence. Current medical LLMs either lack active access to evidence or use retrieved evidence without supervising how it should be appraised and applied during reasoning. To address this, we formalize evidence-based medicine principles as process-level criteria and introduce FaithMed, a framework that combines clinician-designed, automatically refined rubrics with reinforcement learning using step-level process reward assignment and advantage grouping. Across seven medical benchmarks, FaithMed improves over agentic-search baselines (+9% on average) and outcome-only RL (+5.8%), while raising average evidence-based medicine rubric scores over agentic-search Qwen3 baselines (+15.5%). This work demonstrates that explicit step-level supervision can improve both task success and the faithfulness of the reasoning process. Code is available at https://github.com/cxcscmu/FaithMed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。