FaithMed: 训练大语言模型进行忠实于证据的医学推理
FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning
AI总结：
提出FaithMed框架，通过过程级奖励和优势分组强化学习，监督LLM在医学推理中忠实评估和应用检索证据，在7个基准上平均提升9%。
摘要：
忠实推理在医学中至关重要，临床决策需要透明且基于可靠证据的论证。当前的医学LLM要么缺乏主动获取证据的能力，要么使用检索到的证据而不监督其在推理过程中应如何评估和应用。为解决这一问题，我们将循证医学原则形式化为过程级标准，并引入FaithMed框架，该框架结合了临床医生设计的、自动细化的评分标准与使用步骤级过程奖励分配和优势分组的强化学习。在七个医学基准上，FaithMed相比基于智能体搜索的基线（平均+9%）和仅结果RL（+5.8%）有所提升，同时将平均循证医学评分标准分数相比基于智能体搜索的Qwen3基线提高了15.5%。这项工作表明，明确的步骤级监督可以同时提高任务成功率和推理过程的忠实度。代码可在以下网址获取：https://this https URL。
英文摘要：
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.
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。
