Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration

TL;DR

UniKE introduces a unified multimodal editing framework that enhances knowledge reliability, generality, and locality in MLLMs by conceptualizing knowledge as vectorized memories and promoting semantic and truthfulness disentanglement.

Contribution

It proposes a novel unified paradigm for intrinsic and extrinsic knowledge editing in MLLMs, improving knowledge collaboration and balancing key properties.

Findings

Effective knowledge editing with improved reliability, generality, and locality.

Unified framework successfully integrates intrinsic and external knowledge editing.

Code implementation available for reproducibility.

Abstract

The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and weaknesses, struggling to balance the desired properties of reliability, generality, and locality when applied to MLLMs. In this paper, we propose UniKE, a novel multimodal editing method that establishes a unified perspective and paradigm for intrinsic knowledge editing and external knowledge resorting. Both types of knowledge are conceptualized as vectorized key-value memories, with the corresponding editing processes resembling the assimilation and accommodation phases of human cognition, conducted at the same semantic levels. Within such a unified framework, we further promote knowledge collaboration by disentangling the knowledge representations into the semantic and truthfulness spaces. Extensive experiments validate the effectiveness of our method, which ensures that the post-edit MLLM simultaneously maintains excellent reliability, generality, and locality. The code for UniKE is available at \url{https://github.com/beepkh/UniKE}.