FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning
On the map: LLM reasoning → Clinical and biomedical applications
Abstract (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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 18 of its 39 references that are in the map. First posted on arXiv 1 Jul 2026.
Builds on
18 of 39 references.
Closest ancestors · 3
Same direction, newest first
- 2025Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards13 Jun
- 2025MedS3: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision21 Jan
- 2024HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs25 Dec
Other references · 15
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
- 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
- 2025Group-in-Group Policy Optimization for LLM Agent Trainingcited by 442
- 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 382
- 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 319
- 2023MEDITRON-70B: Scaling Medical Pretraining for Large Language Modelscited by 272
- 2024Capabilities of Gemini Models in Medicinecited by 231
- 2025MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understandingcited by 212
- 2022Tevatron: An Efficient and Flexible Toolkit for Dense Retrievalcited by 47
- 2023Effective Large Language Model Adaptation for Improved Grounding and Citation Generationcited by 44
3 more
- 2024Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generationcited by 23
- 2024ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistancecited by 9
- 2026Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Taskscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning
- 2025Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL
- 2025Reasoning LLMs in the Medical Domain: A Literature Survey
- 2026Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning
- 2026Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning
- 2025Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications
- 2025MedCEG: Reinforcing Verifiable Medical Reasoning with Critical Evidence Graph
- 2025Med-R2: Crafting Trustworthy LLM Physicians via Retrieval and Reasoning of Evidence-Based Medicine