医学视觉语言模型的模型编辑评估与理解
Evaluating and Understanding Model Editing for Medical Vision Language Models
AI总结：
针对现有多模态编辑基准不适配临床需求的问题，提出临床基准M3Bench，测试多类编辑方法的性能短板，为医学VLM部署后安全适配提供支撑。
摘要：
模型编辑有望以快速、定向的方式纠正医学视觉语言模型（VLM）部署后的错误，无需高成本的重新训练。但现有多模态模型编辑基准聚焦通用任务，无法反映真实临床领域的需求与变异性。为解决该问题，本文提出M3Bench，这一面向多模态模型编辑的临床基准可评估编辑在图像文本变异、模态与协议偏移、临床知识组合、时间演进等挑战下的可靠性、精确性与泛化性。M3Bench包含覆盖不同解剖结构、模态与专科的16276道问题，支持单次与序列编辑。通过在6个医学及通用VLM上评估4种代表性编辑方法，发现没有方法能在所有指标上表现优异：基于梯度的编辑迁移能力强但存在严重的局部性破坏，基于记忆的编辑可保留局部性却缺乏组合泛化性，且对主干网络相关超参数敏感度高。本文进一步将这些缺陷归因于VLM的隐空间几何特性以及不同编辑方法对其空间分布的改变。总体而言，M3Bench为多模态模型编辑搭建了严格的临床压力测试框架，为更安全的部署后适配提供了可落地的指导。该基准可通过对应公开链接获取。
英文摘要：
Model editing promises a fast, targeted way to correct post-deployment mistakes in medical vision-language models (VLMs) without costly retraining. However, existing multimodal model editing benchmarks focus on general-purpose tasks and do not reflect realistic clinical domain requirements and variability. To address this, we introduce M3Bench, a clinically grounded benchmark for multimodal model editing that evaluates whether an edit remains reliable, precise, and generalizable under the challenges of image and text variation, modality and protocol shifts, clinical knowledge composition, and temporal progression. M3Bench contains 16,276 questions spanning diverse anatomy, modalities, and specialties, and supports both single and sequential edits. By evaluating 4 representative editors across 6 medical and general VLMs, we find that no method excels across all criteria. Gradient-based editors achieve strong transfer but suffer from catastrophic locality violations, whereas memory-based methods preserve locality but lack compositional generality and exhibit high backbone-dependent hyperparameter sensitivity. We further attribute these failures to the latent space geometry of VLMs and how different editing methods shift its landscape. Overall, M3Bench establishes a rigorous clinical stress test for multimodal model editing and offers actionable guidance for safer post-deployment adaptation. The benchmark is publicly available at https://github.com/BioMed-AI-Lab-U-Michgan/M3Bench .
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。
