Skip to main navigation Skip to search Skip to main content

M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model

  • Yang Zhou
  • , Pengfei Cao*
  • , Yubo Chen
  • , Qingbin Liu
  • , Dianbo Sui
  • , Xi Chen
  • , Kang Liu
  • , Jun Zhao*
  • *Corresponding author for this work
  • CAS - Institute of Automation
  • University of Chinese Academy of Sciences
  • Tencent

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Multimodal knowledge editing is an important method for modifying outdated or incorrect knowledge in Multimodal Large Language Models (MLLMs). However, existing datasets for multimodal knowledge editing lack multi-granularity knowledge. In this paper, we present a more realistic dataset called M2Edit, which includes three distinct types of knowledge: entity, relation, and action. Additionally, existing knowledge editing methods for MLLMs lack the ability to handle multi-granularity knowledge and generalize to multimodal data. To address these limitations, we propose the multimodal knowledge editing method MLE. This approach identifies key knowledge layers within different components and collaboratively edits the various components of MLLMs. As a result, we observe significant improvements in visual generality performance, ranging from 4.8% to 10.8%, and achieve the best overall performance on knowledge data of different granularities.

Original languageEnglish
Title of host publicationEMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
EditorsChristos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
PublisherAssociation for Computational Linguistics (ACL)
Pages29029-29042
Number of pages14
ISBN (Electronic)9798891763326
DOIs
StatePublished - 2025
Event30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025 - Suzhou, China
Duration: 4 Nov 20259 Nov 2025

Publication series

NameEMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Conference

Conference30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025
Country/TerritoryChina
CitySuzhou
Period4/11/259/11/25

Fingerprint

Dive into the research topics of 'M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model'. Together they form a unique fingerprint.

Cite this