arXiv cs.AI· Chenlu Ding, Jiancan Wu, Leheng Sheng, Fan Zhang, Yancheng Yuan, Xiang Wang, Xiangnan He·· 11 小时前AI 评分35
MLLMEraser：通过激活引导实现多模态大模型测试时遗忘
MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
AI 导读
MLLMEraser 提出一种无需训练、输入感知的测试时遗忘框架，通过激活引导在不更新参数的情况下动态擦除多模态大模型中的知识。该方法对比对抗扰动下的知识回忆与知识擦除图文对，构建多模态擦除方向，并设计输入感知引导机制自适应决定何时及如何应用。在 LLaVA-1.5 和 Qwen-2.5-VL 上的实验显示，其遗忘效果优于现有 SOTA 基线，计算成本更低且对保留知识的效用损伤极小。
正文 · 原文
Abstract:Multimodal large language models (MLLMs) have demonstrated remarkable capabilities across vision-language tasks, yet their large-scale deployment raises pressing concerns about memorized private data, outdated knowledge, and harmful content. Existing unlearning approaches for MLLMs typically adapt training-based strategies such as gradient ascent or preference optimization, but these methods are computationally expensive, irreversible, and often distort retained knowledge. In this work, we propose MLLMEraser, an input-aware, training-free framework for test-time unlearning. Our approach leverages activation steering to enable dynamic knowledge erasure without parameter updates. Specifically, we construct a multimodal erasure direction by contrasting adversarially perturbed, knowledge-recall image-text pairs with knowledge-erasure counterparts, capturing both textual and visual discrepancies. To prevent unnecessary interference, we further design an input-aware steering mechanism that adaptively determines when and how the erasure direction should be applied, preserving utility on retained knowledge while enforcing forgetting on designated content. Experiments on LLaVA-1.5 and Qwen-2.5-VL demonstrate that MLLMEraser consistently outperforms state-of-the-art MLLM unlearning baselines, achieving stronger forgetting performance with lower computational cost and minimal utility degradation.
| Comments: | Accepted at NeurIPS 2026 (40th Conference on Neural Information Processing Systems) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2510.04217 [cs.LG] |
| (or arXiv:2510.04217v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2510.04217 arXiv-issued DOI via DataCite |
Submission history
From: Chenlu Ding [view email]
[v1]
Sun, 5 Oct 2025 14:20:17 UTC (891 KB)
[v2]
Fri, 10 Oct 2025 11:47:30 UTC (890 KB)
[v3]
Mon, 2 Feb 2026 12:41:26 UTC (965 KB)
[v4]
Fri, 30 Oct 2026 08:25:33 UTC (1,090 KB)
来源：arXiv cs.AI · arxiv.org