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

• URL: http://arxiv.org/abs/2505.13973v1
• Date: Tue, 20 May 2025 06:12:20 GMT
• Title: Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
• Authors: Wenhui Zhu, Xuanzhao Dong, Xin Li, Peijie Qiu, Xiwen Chen, Abolfazl Razi, Aris Sotiras, Yi Su, Yalin Wang,
• Abstract summary: reinforcement learning (RL)-based tuning has shifted the trajectory of Multimodal Large Language Models (MLLMs)<n>We investigate four critical dimensions that affect the effectiveness of RL-based tuning in medical visual question answering (VQA)<n>We conduct extensive experiments to analyze these factors for medical MLLMs, providing new insights into how models are domain-specifically fine-tuned.
• Score: 15.870555147672023
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency [52.50039435394964]
  We systematically evaluate foundation models for regression-based tasks.<n>We extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models.<n>Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts.
  arXiv  Detail & Related papers  (2026-01-29T14:06:50Z)
• MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement [63.82954136824963]
  Medical Vision-Language Models excel at perception tasks with complex clinical reasoning required in real-world scenarios.<n>We propose a novel reasoning MedVLM that addresses these challenges through domain-specific adaptation and guideline reinforcement.
  arXiv  Detail & Related papers  (2026-01-16T02:32:07Z)
• Clinical-R1: Empowering Large Language Models for Faithful and Comprehensive Reasoning with Clinical Objective Relative Policy Optimization [28.610758740650407]
  We introduce Clinical-Objective Relative Policy Optimization (CRPO), a scalable, multi-objective, verifiable reinforcement learning method.<n>CRPO integrates rule-based and verifiable reward signals that jointly optimize accuracy, faithfulness, and comprehensiveness without relying on human annotation.
  arXiv  Detail & Related papers  (2025-11-29T19:09:24Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Prediction [2.904892426557913]
  Large language models (LLMs) have shown strong performance in biomedical NLP.<n>We present a unified, multi-task learning framework that aligns autoregressive LLMs with clinical reasoning for outcome prediction.<n>Our findings underscore the importance of reasoning-aware alignment in multi-task clinical modeling.
  arXiv  Detail & Related papers  (2025-10-20T13:35:12Z)
• Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning [15.73558614478585]
  We introduce MM-Retinal-Reason, the first ophthalmic multimodal dataset with the full spectrum of perception and reasoning.<n>Building upon MM-Retinal-Reason, we propose OphthaReason, the first ophthalmology-specific multimodal reasoning model with step-by-step reasoning traces.<n>Our model achieves state-of-the-art performance on both basic and complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-08-22T06:47:30Z)
• Model Reprogramming Demystified: A Neural Tangent Kernel Perspective [49.42322600160337]
  We present a comprehensive theoretical analysis of Model Reprogramming (MR) through the lens of the Neural Tangent Kernel (NTK) framework.<n>We demonstrate that the success of MR is governed by the eigenvalue spectrum of the NTK matrix on the target dataset.<n>Our contributions include a novel theoretical framework for MR, insights into the relationship between source and target models, and extensive experiments validating our findings.
  arXiv  Detail & Related papers  (2025-05-31T16:15:04Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models [79.41859481668618]
  Large Language Models (LLMs) have significantly advanced the fact-checking studies.<n>Existing automated fact-checking evaluation methods rely on static datasets and classification metrics.<n>We introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities.
  arXiv  Detail & Related papers  (2025-02-25T07:44:22Z)
• Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling [87.17041933863041]
  Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs)<n>We introduce a $textbfR$esponse-$textbfc$onditioned $textbfB$radley-$textbfT$erry (Rc-BT) model that enhances the model's capability in length bias mitigating and length instruction following.<n>We also propose the Rc-RM and Rc-DPO algorithm to leverage the Rc-BT model for reward modeling and direct policy optimization
  arXiv  Detail & Related papers  (2025-02-02T14:50:25Z)
• Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning [104.27224674122313]
  Fine-tuning MLLM has become a common practice to improve performance on specific downstream tasks. To balance the trade-off between generalization and specialization, we propose measuring the parameter importance for both pre-trained and fine-tuning distributions.
  arXiv  Detail & Related papers  (2024-11-17T01:16:37Z)
• Stronger Baseline Models -- A Key Requirement for Aligning Machine Learning Research with Clinical Utility [0.0]
  Well-known barriers exist when attempting to deploy Machine Learning models in high-stakes, clinical settings. We show empirically that including stronger baseline models in evaluations has important downstream effects. We propose some best practices that will enable practitioners to more effectively study and deploy ML models in clinical settings.
  arXiv  Detail & Related papers  (2024-09-18T16:38:37Z)
• ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Tasks [22.539696532725607]
  Large Language Models (LLMs) are increasingly deployed in medicine.<n>However, their utility in non-generative clinical prediction remains under-evaluated.<n>Our ClinicRealm study addresses this by benchmarking 9 GPT-based LLMs, 5 BERT-based models, and 7 traditional methods on unstructured clinical notes and structured Electronic Health Records.
  arXiv  Detail & Related papers  (2024-07-26T06:09:10Z)
• XAI4LLM. Let Machine Learning Models and LLMs Collaborate for Enhanced In-Context Learning in Healthcare [16.79952669254101]
  We introduce a knowledge-guided in-context learning framework to enable large language models to process structured clinical data.<n>Our approach integrates domain-specific feature groupings, carefully balanced few-shot examples, and task-specific prompting strategies.
  arXiv  Detail & Related papers  (2024-05-10T06:52:44Z)
• Unveiling the Generalization Power of Fine-Tuned Large Language Models [81.70754292058258]
  We investigate whether fine-tuning affects the intrinsic generalization ability intrinsic to Large Language Models (LLMs) Our main findings reveal that models fine-tuned on generation and classification tasks exhibit dissimilar behaviors in generalizing to different domains and tasks. We observe that integrating the in-context learning strategy during fine-tuning on generation tasks can enhance the model's generalization ability.
  arXiv  Detail & Related papers  (2024-03-14T08:18:59Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback [19.564416963801268]
  We propose an approach called preference learning from process feedback. PLPF integrates the doctor's diagnostic logic into LLMs. We show that PLPF enhances the diagnostic accuracy of the baseline model in medical conversations by 17.6%.
  arXiv  Detail & Related papers  (2024-01-11T06:42:45Z)
• Natural Language Programming in Medicine: Administering Evidence Based Clinical Workflows with Autonomous Agents Powered by Generative Large Language Models [29.05425041393475]
  Generative Large Language Models (LLMs) hold significant promise in healthcare. This study assessed the potential of LLMs to function as autonomous agents in a simulated tertiary care medical center.
  arXiv  Detail & Related papers  (2024-01-05T15:09:57Z)
• Meta Transfer of Self-Supervised Knowledge: Foundation Model in Action for Post-Traumatic Epilepsy Prediction [0.6291443816903801]
  We introduce a novel training strategy for our foundation model. We demonstrate that the proposed strategy significantly improves task performance on small-scale clinical datasets. Results further demonstrated the enhanced generalizability of our foundation model.
  arXiv  Detail & Related papers  (2023-12-21T07:42:49Z)
• Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records [57.75125067744978]
  We propose a data augmentation method to facilitate domain adaptation. adversarially generated samples are used during domain adaptation. Results confirm the effectiveness of our method and the generality on different tasks.
  arXiv  Detail & Related papers  (2021-01-13T03:20:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.