@inproceedings{zhou-etal-2025-m2edit,
    title = "{M}2{E}dit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model",
    author = "Zhou, Yang  and
      Cao, Pengfei  and
      Chen, Yubo  and
      Liu, Qingbin  and
      Sui, Dianbo  and
      Chen, Xi  and
      Liu, Kang  and
      Zhao, Jun",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1478/",
    pages = "29017--29030",
    ISBN = "979-8-89176-332-6",
    abstract = "Multimodal knowledge editing is an important method for modifying outdated or incorrect knowledge in Multimodal Large Language Models (MLLMs).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."
}