让多模态模型的编辑更通用，能跨不同表达保持一致效果。
Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment
- 通过对抗性变体生成暴露脆弱语义区域，提升编辑鲁棒性。
- 在多个知识单元内实现一致预测，验证了编辑的泛化能力。
- 适合需要稳定更新知识的多模态应用，如视觉问答与生成。
多模态大语言模型需高效更新知识而不损害已有能力。现有内在知识编辑虽可靠且局部性强，但泛化能力有限，难以在语义等价的视觉与语言变体间传播修改。问题源于缺乏显式语义监督、编辑范围僵化及高维多模态空间中对单一样本的偏差锚定。本文提出通过显式目标增强泛化性，将鲁棒性形式化为包含语义等价多模态输入的知识单元，并定义泛化性为单元内预测一致性。引入隐空间对抗鲁棒化（LAR）生成语义连贯的对抗变体以暴露脆弱区域；进一步提出秩约束子空间学习（RCSL），通过基于奇异值的目标在编辑层强制对抗表示的低秩对齐。大量实验验证了ASAM方法的有效性。
原文摘要 · Abstract (English)
Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimodal knowledge editing achieves strong reliability and locality, it often exhibits limited generality, failing to propagate edits across semantically equivalent visual and linguistic variations. This issue arises from the lack of explicit semantic supervision, rigid editing scopes, and biased anchoring to individual samples in high-dimensional multimodal spaces. We address robust intrinsic multimodal knowledge editing by explicitly targeting generalization. We formalize robustness through knowledge units that group semantically equivalent multimodal inputs and define generality as consistent predictions within each unit. To expose fragile semantic regions, we introduce Latent Adversarial Robustification (LAR), which generates adversarial yet semantically coherent variants in the joint latent space. We further propose Rank-Constrained Subspace Learning (RCSL), enforcing low-rank alignment of adversarial representations at the edit layer via a singular value-based objective. Extensive analysis demonstrates the effectiveness of ASAM empirically.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。