MultiMedEdit：一个用于评估医疗 VQA 中知识编辑的场景感知基准
MultiMedEdit: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA
AI总结：
本文提出首个评估医疗多模态VQA知识编辑的场景感知基准MultiMedEdit，通过三维指标和跨范式实验揭示现有方法在泛化、长尾推理及部署效率上的局限，为开发临床稳健的KE技术奠定基础。
摘要：
知识编辑（KE）提供了一种可扩展的方法，用于更新大型语言模型中的事实知识，而无需进行完全重新训练。尽管先前的研究已经证明了其在通用领域和医疗问答任务中的有效性，但很少有人关注多模态医疗场景中的 KE。与纯文本设置不同，医疗 KE 要求将更新后的知识与视觉推理相结合，以支持安全且可解释的临床决策。为了解决这一空白，我们提出了 MultiMedEdit，这是第一个专为评估临床多模态任务中的 KE 而设计的基准。我们的框架涵盖了理解和推理任务类型，定义了一个三维指标套件（可靠性、通用性和局部性），并支持跨通用模型和领域特定模型的跨范式比较。我们在单次编辑和终身编辑设置下进行了广泛实验。结果表明，当前方法在泛化和长尾推理方面存在困难，特别是在复杂的临床工作流程中。我们进一步提出了一项效率分析（例如，编辑延迟、内存占用），揭示了 KE 范式中现实世界部署的实际权衡。总体而言，MultiMedEdit 不仅揭示了当前方法的局限性，而且为未来开发临床稳健的知识编辑技术提供了坚实的基础。
英文摘要：
Knowledge editing (KE) provides a scalable approach for updating factual knowledge in large language models without full retraining. While previous studies have demonstrated effectiveness in general domains and medical QA tasks, little attention has been paid to KE in multimodal medical scenarios. Unlike text-only settings, medical KE demands integrating updated knowledge with visual reasoning to support safe and interpretable clinical decisions. To address this gap, we propose MultiMedEdit, the first benchmark tailored to evaluating KE in clinical multimodal tasks. Our framework spans both understanding and reasoning task types, defines a three-dimensional metric suite (reliability, generality, and locality), and supports cross-paradigm comparisons across general and domain-specific models. We conduct extensive experiments under single-editing and lifelong-editing settings. Results suggest that current methods struggle with generalization and long-tail reasoning, particularly in complex clinical workflows. We further present an efficiency analysis (e.g., edit latency, memory footprint), revealing practical trade-offs in real-world deployment across KE paradigms. Overall, MultiMedEdit not only reveals the limitations of current approaches but also provides a solid foundation for developing clinically robust knowledge editing techniques in the future.
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。
