Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models 事件

Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models arXiv:2605.29826v1 Announce Type: new Abstract: Existing methods in Multimodal Knowledge Editing (MKE) have advanced the ability to correct outdated or inaccurate knowledge in Multimodal Large Language Models (MLLMs). However, they exhibit a critical limitation: while effectively modifying target factual pairs, they fail to generalize edits to logically related queries and often cause unintended alteration