# Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models

Source: [Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models](<https://www.sota2.com/research/paper/68fa78ab1e209131cea79c0d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:44:13.662Z

Authors: Wenhui Zhu, Xuanzhao Dong, Xin Li, Peijie Qiu, Xiwen Chen, Abolfazl Razi, Aris Sotiras, Yi Su, Yalin Wang

Published: 2025-05-20T06:12:20.000Z

## Abstract

Recently, reinforcement learning (RL)-based tuning has shifted the trajectory of Multimodal Large Language Models (MLLMs), particularly following the introduction of Group Relative Policy Optimization (GRPO). However, directly applying it to medical tasks remains challenging for achieving clinically grounded model behavior. Motivated by the need to align model response with clinical expectations, we investigate four critical dimensions that affect the effectiveness of RL-based tuning in medical visual question answering (VQA): base model initialization strategy, the role of medical semantic alignment, the impact of length-based rewards on long-chain reasoning, and the influence of bias. We conduct extensive experiments to analyze these factors for medical MLLMs, providing new insights into how models are domain-specifically fine-tuned. Additionally, our results also demonstrate that GRPO-based RL tuning consistently outperforms standard supervised fine-tuning (SFT) in both accuracy and reasoning quality.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.13973>)

[PDF](<https://arxiv.org/pdf/2505.13973.pdf>)
