Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment

About

Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimodal knowledge editing achieves strong reliability and locality, it often exhibits limited generality, failing to propagate edits across semantically equivalent visual and linguistic variations. This issue arises from the lack of explicit semantic supervision, rigid editing scopes, and biased anchoring to individual samples in high-dimensional multimodal spaces. We address robust intrinsic multimodal knowledge editing by explicitly targeting generalization. We formalize robustness through knowledge units that group semantically equivalent multimodal inputs and define generality as consistent predictions within each unit. To expose fragile semantic regions, we introduce Latent Adversarial Robustification (LAR), which generates adversarial yet semantically coherent variants in the joint latent space. We further propose Rank-Constrained Subspace Learning (RCSL), enforcing low-rank alignment of adversarial representations at the edit layer via a singular value-based objective. Extensive analysis demonstrates the effectiveness of ASAM empirically.

Haoyuan Wang, Xiaohao Liu, Jiajie Su, Jianmao Xiao, Chaochao Chen• 2026

Related benchmarks

TaskDatasetResultRank
Knowledge EditingMMEdit E-IC
Reliability99.88
26
Edited Image CaptioningMMEdit E-IC
Reliability100
20
Edited Visual Question AnsweringMMEdit E-VQA
Reliability100
20
Knowledge EditingE-VQA
Reliability100
10
Showing 4 of 4 rows

Other info

Follow for update