FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning

2026-07-01 · Zhiyun Zhang, Liwen Sun, Xiang Qian, Chenyan Xiong arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.01440

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence

2026-01-17 · Kaijie Mo, Siddhartha Venkatayogi, Chantal Shaib, Ramez Kouzy 외 arxiv

In high-stakes domains like medicine, it may be generally desirable for models to faithfully adhere to the context provided. But what happens if the context does not align with model priors or safety protocols? In this p…

Auditing Evidence Use in Medical LLM Diagnosis

2026-07-23 · Junchi Liao, Jiawen Deng, Fuji Ren arxiv

Medical LLMs are often evaluated by whether they select the correct diagnosis, but diagnostic accuracy alone does not show whether the model used the case evidence appropriately. We present a behavioral audit of evidence…

Medical Diagnosis

Dissociation of Faithful and Unfaithful Reasoning in LLMs

2024-05-23 · Evelyn Yee, Alice Li, Chenyu Tang, Yeon Ho Jung 외

Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thou…

Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style

2024-09-17 · Yuepei Li, Kang Zhou, Qiao Qiao, Bach Nguyen 외

Retrieval-augmented generation (RAG) improves Large Language Models (LLMs) by incorporating external information into the response generation process. However, how context-faithful LLMs are and what factors influence LLM…

Natural Questions RAG Response Generation Retrieval-augmented Generation

Faithful Summarization of Consumer Health Queries: A Cross-Lingual Framework with LLMs

2025-11-13 · Ajwad Abrar, Nafisa Tabassum Oeshy, Prianka Maheru, Farzana Tabassum 외 arxiv

Summarizing consumer health questions (CHQs) can ease communication in healthcare, but unfaithful summaries that misrepresent medical details pose serious risks. We propose a framework that combines TextRank-based senten…

Medical Named Entity Recognition Text Summarization