@inproceedings{li-etal-2026-sgpvt,
    title = "{SGPVT}: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in {MLLM} Unlearning",
    author = "Li, Jiaqi  and
      Zhang, Zhijing  and
      Geng, Jiahui  and
      Bi, Sheng  and
      Zhang, Chuanyi  and
      Liu, Fan  and
      Qi, Guilin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.442/",
    pages = "9744--9763",
    ISBN = "979-8-89176-390-6",
    abstract = "Machine unlearning in multimodal large language models (MLLMs) aims to remove specific concepts while preserving overall utility. However, existing approaches focus primarily on general utility metrics, overlooking the preservation of semantically related concepts. We present the first systematic analysis of this proximal collateral damage, revealing that forgetting vulnerability correlates strongly with visual embedding similarity in a smooth gradient across the semantic space. Based on this insight, we propose a novel unlearning framework that introduces Self-Generated Proximal Visual Tokens (SGPVTs), which are synthetically perturbed visual representations around the target concept. Our method employs an adaptive cosine-band curriculum with a dual-stream objective: forgetting the target via gradient ascent while distilling knowledge from a frozen teacher model into proximal tokens to prevent degradation. Extensive experiments demonstrate that our approach significantly outperforms existing methods in preserving semantically related concepts while achieving effective target unlearning, eliminating the need for manual retention set curation. Our source code will be released in the near future."
}