mlsanityData to 14 Oct 2026

MedFact-R1: Towards Factual Medical Reasoning via Pseudo-Label Augmentation

arXiv 2509.15154 ↗First posted 18 Sep 2025cs.CVcited by 1

On the map: LLM reasoning → Clinical and biomedical applications

also in 1 more
Abstract (arXiv)

Ensuring factual consistency and reliable reasoning remains a critical challenge for medical vision-language models. We introduce MEDFACT-R1, a two-stage framework that integrates external knowledge grounding with reinforcement learning to improve the factual medical reasoning. The first stage uses pseudo-label supervised fine-tuning (SFT) to incorporate external factual expertise; while the second stage applies Group Relative Policy Optimization (GRPO) with four tailored factual reward signals to encourage self-consistent reasoning. Across three public medical QA benchmarks, MEDFACT-R1 delivers up to 22.5% absolute improvement in factual accuracy over previous state-of-the-art methods. Ablation studies highlight the necessity of pseudo-label SFT cold start and validate the contribution of each GRPO reward, underscoring the synergy between knowledge grounding and RL-driven reasoning for trustworthy medical AI. Codes are released at https://github.com/Garfieldgengliang/MEDFACT-R1.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 17 of its 21 references that are in the map. First posted on arXiv 18 Sep 2025.

Builds on

17 of 21 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization1 Jul
  2. 2025MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning31 May

Other references · 15

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  8. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  9. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 597
  10. 2020Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generationcited by 141
  11. 2024MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Modelscited by 85
  12. 2022Improving the Factual Correctness of Radiology Report Generation with Semantic Rewardscited by 83
3 more
  1. 2024FairCLIP: Harnessing Fairness in Vision-Language Learningcited by 69
  2. 2024RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Modelscited by 60
  3. 2025SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Rewardcited by 45

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correctioncited by 8

Similar, not cited

Close in wording, no citation either way

  1. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models
  2. 2025Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation
  3. 2026MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement
  4. 2025Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
  5. 2026MediX-R1: Open Ended Medical Reinforcement Learning
  6. 2025MedVLThinker: Simple Baselines for Multimodal Medical Reasoning
  7. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
  8. 2025Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning