Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment

Abstract

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.

Workflow Status

Review status

pending

Role

unreviewed

Read priority

soon

Vote

Not set.

Saved

no

Collections

Not filed yet.

Next action

Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

Similar Papers

BibTeX

@article{wang2026beyond,
  title = {Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment},
  author = {Haoyuan Wang and Xiaohao Liu and Jiajie Su and Jianmao Xiao and Chaochao Chen},
  year = {2026},
  abstract = {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 mult},
  url = {https://arxiv.org/abs/2605.23780},
  keywords = {cs.AI},
  eprint = {2605.23780},
  archiveprefix = {arXiv},
}

Metadata

{}