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

arXiv: https://arxiv.org/abs/2509.15154 · HTML: https://mlsanity.com/paper/2509.15154/

## Key facts

- Cited by 1 papers 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.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation](https://mlsanity.com/paper/2010.10042/) (2020)
- [MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models](https://mlsanity.com/paper/2410.13085/) (2024)
- [Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards](https://mlsanity.com/paper/2210.12186/) (2022)
- [FairCLIP: Harnessing Fairness in Vision-Language Learning](https://mlsanity.com/paper/2403.19949/) (2024)
- [RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models](https://mlsanity.com/paper/2407.05131/) (2024)
- [SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward](https://mlsanity.com/paper/2505.17018/) (2025)
- [MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning](https://mlsanity.com/paper/2506.00555/) (2025)
- [MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization](https://mlsanity.com/paper/2507.02994/) (2025)

## Built on by (most cited first, 1 of 1)

- [MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction](https://mlsanity.com/paper/2510.03687/) (2025)

## 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.