MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency
Year: 2025
Type: conference-paper
Abstract: Multimodal large language models (MLLMs) are prone to non-factual or outdated knowledge issues, highlighting the importance of knowledge editing.Many benchmark has been proposed for researching multimodal knowledge editing.However, previous benchmarks focus on limited scenarios due to the lack of rigorous definition of multimodal knowledge.To better evaluate multimodal knowledge editing, we propose a decomposed definition of multimodal knowledge.Following the decomposed definition of multimodal knowledge, we introduce three scenarios and a novel requirement modality consistency.We construct MC-MKE, a fine-grained Multimodal Knowledge Editing benchmark emphasizing Modality Consistency through strict data selection.We evaluate several multimodal knowledge editing methods on MC-MKE, revealing their limitations, particularly in terms of modality consistency.Our work highlights the challenges posed by multimodal knowledge editing and motivates further research in developing effective techniques for this task. 1
Authors: Junzhe Zhang, Huixuan Zhang, Xunjian Yin, Baizhou Huang, Xu Zhang, Xinyu Hu, Xiaojun Wan
Institution: Peking University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4412887784