ClinCoT：面向医学视觉语言模型的临床感知视觉推理链
ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models
AI总结：
ClinCoT通过引入临床感知的视觉推理链框架，提升医学视觉语言模型在临床决策中的事实性支撑与多模态推理能力。
摘要：
医学视觉-语言模型在临床决策支持中展现出 promising 的潜力，但仍然由于缺乏对局部病理证据的充分支撑而容易产生事实性幻觉。现有的医学对齐方法主要通过偏好优化在响应层面进行操作，虽然提高了输出的正确性，但使中间推理与视觉区域之间的联系变得薄弱。尽管推理链（CoT）增强了多模态推理能力，但其仍然以文本为中心，限制了临床视觉线索的有效整合。为了解决这一差距，我们提出了ClinCoT，一种具有临床感知的视觉推理链框架，将偏好优化从响应层面的纠正转变为以视觉驱动的推理。我们引入了一个自动数据生成管道，通过假设驱动的区域提议进行推理来构建临床支撑的偏好对。多个Med-LLMs评估者对每个响应进行排名和评分，这些排名用作训练目标模型的监督。我们进一步引入了一种基于评分的边际意识优化策略，该策略结合了偏好排名和评分差异来优化区域级别的推理轨迹。为了在模型政策随训练演变时保持对齐，我们采用了一种迭代学习方案，动态重新生成偏好数据。在三个医学VQA和报告生成基准测试中进行了广泛的实验，结果表明，ClinCoT在事实性支撑方面持续改进，并在现有基于偏好的对齐方法上取得了更优的表现。
英文摘要：
Medical Vision-Language Models have shown promising potential in clinical decision support, yet they remain prone to factual hallucinations due to insufficient grounding in localized pathological evidence. Existing medical alignment methods primarily operate at the response level through preference optimization, improving output correctness but leaving intermediate reasoning weakly connected to visual regions. Although chain-of-thought (CoT) enhances multimodal reasoning, it remains largely text-centric, limiting effective integration of clinical visual cues. To address this gap, we propose ClinCoT, a clinical-aware visual chain-of-thought framework that transforms preference optimization from response-level correction to visual-driven reasoning. We introduce an automatic data generation pipeline that constructs clinically grounded preference pairs through reasoning with hypotheses-driven region proposals. Multiple Med-LLMs evaluators rank and assign scores to each response, and these rankings serve as supervision to train the target model. We further introduce a scoring-based margin-aware optimization strategy that incorporates both preference ranking and score difference to refine region-level reasoning trajectories. To maintain alignment as the model's policy evolves during training, we adopt an iterative learning scheme that dynamically regenerates preference data. Extensive experiments on three medical VQA and report generation benchmarks demonstrate that ClinCoT consistently improves factual grounding and achieves superior performance compared with existing preference-based alignment methods.
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。
