arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.01236cs.CLcs.LG
收藏

GRPO++:低资源环境下增强皮肤病学推理能力

GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings

Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology (BUET)(电气与电子工程系,孟加拉国工程与技术大学)

Ismam Nur Swapnil, Aranya Saha, Tanvir Ahmed Khan, Mohammad Ariful Haque

AI总结:

针对低资源下皮肤病学VLM推理受限的问题,提出GRPO++优化GRPO训练稳定性,结合多阶段训练流程与知识图谱辅助的DPO对齐,在皮肤病数据集上实现性能提升,为资源受限场景下开发专业VLM提供可行方案。

摘要:

视觉语言模型(VLM)在医学图像分析中展现出应用前景,但其在皮肤病学等复杂领域的结构化推理能力,往往受限于数据稀缺以及先进训练技术的高计算成本。为应对这些挑战,我们提出DermIQ-VLM——一种通过多阶段、资源高效型方法开发的VLM,旨在模拟皮肤科医生的诊断流程。我们的核心贡献是改进版的分组相对策略优化(Grouped Relative Policy Optimization, GRPO),命名为GRPO++,它能稳定功能强大但数据需求高的GRPO框架。我们提出的训练流程首先采用GRPO++实现面向推理的疾病识别,随后通过监督微调提升对话能力。为缓解该步骤中产生的事实性错误,我们接着利用基于知识图谱的系统作为专家偏好的可扩展替代方案,通过直接偏好优化(DPO)对模型进行对齐。在一个精心整理的皮肤病学数据集上的初步评估表明,我们提出的方法相较于标准微调方法取得了显著的性能提升。这些结果验证了我们的训练流程在资源受限环境下,作为开发专业、可靠的VLM的可行路径的潜力。

英文摘要:

Vision-Language Models (VLMs) show promise in medical image analysis, yet their capacity for structured reasoning in complex domains like dermatology is often limited by data scarcity and the high computational cost of advanced training techniques. To address these challenges, we introduce DermIQ-VLM, a VLM developed through a multi-stage, resource-efficient methodology designed to emulate a dermatologist's diagnostic process. Our primary contribution is a modified version of Grouped Relative Policy Optimization (GRPO), called GRPO++, which stabilizes the powerful but data-intensive GRPO framework. Our proposed training pipeline first employs GRPO++ for reasoning-oriented disease recognition, followed by supervised fine-tuning for conversational ability. To mitigate factual errors introduced during this step, we then align the model using Direct Preference Optimization (DPO), leveraging a Knowledge Graph-based system as a scalable proxy for expert preference. A preliminary evaluation on a curated dermatological dataset demonstrates that our proposed methodology yields notable performance gains over standard fine-tuning approaches. These findings validate the potential of our pipeline as a feasible pathway for developing specialized, reliable VLMs in resource-constrained environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑