面向推理保持的多模态大语言模型遗忘
Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
提出一种无需训练、在推理时通过子空间引导和自适应转向来遗忘答案与推理痕迹的方法，可复用于多模态大模型的安全对齐与隐私保护，同时保持通用推理能力。
原文依据 a training-free and inference-time intervention framework that steers internal representations to forget both answers and reasoning traces while explicitly preserving general reasoning
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论机器遗忘旨在从已训练模型中擦除所请求的数据，而无需完全重新训练。对于推理多模态大语言模型（RMLLMs），这一任务尤为独特地具有挑战性：即使最终答案被遗忘，中间思维链步骤仍可能泄露敏感信息，而过激的干预容易损害通用推理能力。然而，尚无基准同时评估遗忘方法在抑制推理层面泄露与保持推理能力方面的表现。我们通过 RMLLMU-Bench 填补这一空白，这是首个面向 RMLLM 遗忘的基准，在标准遗忘指标基础上扩展了推理泄露与推理保持的专用度量。在 RMLLMU-Bench 上的系统评估揭示，现有面向 MLLM 和大型（语言）推理模型（LRMs）的遗忘方法要么在推理过程中留下大量泄露，要么严重降低推理性能。为解决这些不足，我们提出 R-MUSE（通过子空间引导与自适应转向实现推理保持的 MLLM 遗忘），一种无需训练、在推理时进行干预的框架，引导内部表征遗忘答案与推理痕迹，同时显式保持通用推理能力。在 RMLLMU-Bench 上的实验表明，R-MUSE 在有效遗忘与推理保持之间实现了显著更好的平衡。
英文原文摘要 1449 字符
Machine unlearning aims to erase requested data from trained models without full retraining. For Reasoning Multimodal Large Language Models (RMLLMs), this is uniquely challenging: intermediate chain-of-thought steps can still leak sensitive information even when final answers are forgotten, and overly aggressive interventions easily damage general reasoning ability. Yet no benchmark jointly evaluates how well unlearning methods suppress reasoning-level leakage while preserving reasoning competence. We address this gap with RMLLMU-Bench, the first benchmark for RMLLM unlearning that extends standard forgetting metrics with dedicated measures of reasoning leakage and reasoning retention. A systematic evaluation on RMLLMU-Bench reveals that existing unlearning methods for MLLMs and Large (Language) Reasoning Models (LRMs) either leave substantial leakage in the reasoning process or severely degrade reasoning performance. To address these gaps, we propose R-MUSE (\underline R easoning-preserving \underline M LLM \underline U nlearning via \underline S ubspace guidance and Adaptive St \underline E ering), a training-free and inference-time intervention framework that steers internal representations to forget both answers and reasoning traces while explicitly preserving general reasoning. Experiments on RMLLMU-Bench demonstrate that R-MUSE achieves a substantially better balance between effective forgetting and reasoning retention.