遗忘哪些概念与如何拒绝？面向大型视觉语言模型持续遗忘的概念分解
Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
把「遗忘」从整模型级细化到视觉-语言概念组合级，并用概念驱动的 MoE 路由复用拒绝专家，为 LVLM 安全对齐与顺序删除请求提供可复用框架；做多模态安全/隐私的读者可直接借用其概念调制器与 refuser 路由设计。
原文依据 grounds refusal behavior in fine-grained descriptions of visual and textual concepts decomposed from deletion targets
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论持续遗忘（continual unlearning）面临的挑战是：使大型视觉语言模型能够针对顺序到来的删除请求，选择性地拒绝特定的图像-指令对，同时保持通用能力。然而，顺序的遗忘更新会扭曲共享表征，在视觉-语言对与拒绝行为之间产生虚假关联，从而妨碍对拒绝目标的精确识别，导致不恰当的拒绝。为应对这一挑战，我们提出一种新的持续遗忘框架，将拒绝行为建立在从删除目标中分解出的视觉与文本概念的细粒度描述之上。我们首先通过概念调制器识别哪些视觉-语言概念组合刻画了每个遗忘类别，然后通过一组拒绝专家（称为 refusers）确定如何生成恰当的拒绝响应，每个专家专门负责与概念对齐的拒绝生成。为在顺序任务间生成概念特定的拒绝响应，我们引入一种多模态、概念驱动的路由方案，对概念相似的任务复用 refusers，并将未被充分利用的 refusers 适配到新概念上。在视觉-语言基准上的大量实验表明，该框架通过生成基于概念的拒绝响应并在遗忘序列中保持通用能力，优于现有方法。
英文原文摘要 1426 字符
Continual unlearning poses the challenge of enabling large vision-language models to selectively refuse specific image-instruction pairs in response to sequential deletion requests, while preserving general utility. However, sequential unlearning updates distort shared representations, creating spurious associations between vision-language pairs and refusal behaviors that hinder precise identification of refusal targets, resulting in inappropriate refusals. To address this challenge, we propose a novel continual unlearning framework that grounds refusal behavior in fine-grained descriptions of visual and textual concepts decomposed from deletion targets. We first identify which visual-linguistic concept combinations characterize each forget category through a concept modulator, then determine how to generate appropriate refusal responses via a mixture of refusal experts, termed refusers, each specialized for concept-aligned refusal generation. To generate concept-specific refusal responses across sequential tasks, we introduce a multimodal, concept-driven routing scheme that reuses refusers for tasks sharing similar concepts and adapts underutilized ones for novel concepts. Extensive experiments on vision-language benchmarks demonstrate that the proposed framework outperforms existing methods by generating concept-grounded refusal responses and preserving the general utility across unlearning sequences.