Guardado en:
Detalles Bibliográficos
Autores principales: Zeng, Zhen, Gu, Leijiang, Duan, Zhangling, Li, Feng, Shi, Zenglin, Snoek, Cees G. M., Wang, Meng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.20196
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909922873049088
author Zeng, Zhen
Gu, Leijiang
Duan, Zhangling
Li, Feng
Shi, Zenglin
Snoek, Cees G. M.
Wang, Meng
author_facet Zeng, Zhen
Gu, Leijiang
Duan, Zhangling
Li, Feng
Shi, Zenglin
Snoek, Cees G. M.
Wang, Meng
contents Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information. Although existing unlearning methods can remove such knowledge, they fail to achieve benign forgetting because they often degrade the model's general image understanding performance. To address this, we propose the Sculpted Memory Forgetting Adapter (SMFA), which confines forgetting to targeted memory regions while preserving overall capabilities. SMFA first fine-tunes the model to replace sensitive responses with refusals, yielding a memory forgetting adapter, and then applies a retaining anchor-guided masking mechanism to prevent interference with unrelated knowledge and understanding ability. To systematically evaluate selective MLLM unlearning, we introduce S-MLLMUn Bench, the first benchmark designed to jointly assess the removal of sensitive knowledge and retention of general visual understanding. Extensive experiments show that, unlike prior methods, SMFA achieves precise and controllable unlearning while maintaining the model's foundational image understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20196
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
Zeng, Zhen
Gu, Leijiang
Duan, Zhangling
Li, Feng
Shi, Zenglin
Snoek, Cees G. M.
Wang, Meng
Artificial Intelligence
Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information. Although existing unlearning methods can remove such knowledge, they fail to achieve benign forgetting because they often degrade the model's general image understanding performance. To address this, we propose the Sculpted Memory Forgetting Adapter (SMFA), which confines forgetting to targeted memory regions while preserving overall capabilities. SMFA first fine-tunes the model to replace sensitive responses with refusals, yielding a memory forgetting adapter, and then applies a retaining anchor-guided masking mechanism to prevent interference with unrelated knowledge and understanding ability. To systematically evaluate selective MLLM unlearning, we introduce S-MLLMUn Bench, the first benchmark designed to jointly assess the removal of sensitive knowledge and retention of general visual understanding. Extensive experiments show that, unlike prior methods, SMFA achieves precise and controllable unlearning while maintaining the model's foundational image understanding.
title Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
topic Artificial Intelligence
url https://arxiv.org/abs/2511.20196