Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
This work addresses the problem of aligning model responses with clinical expectations in medical VQA, representing an incremental improvement in domain-specific fine-tuning.
The paper tackled the challenge of applying reinforcement learning fine-tuning to medical visual question answering by investigating four critical dimensions affecting its effectiveness, and demonstrated that GRPO-based tuning outperforms standard supervised fine-tuning in accuracy and reasoning quality.
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.