转向说不：通过激活转向实现可配置拒绝在视觉语言模型中
Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
AI总结：
本文提出CR-VLM，通过激活转向实现视觉语言模型中的可配置拒绝，解决现有拒绝策略无法适应多样化需求的问题，提升模型的安全性和适应性。
摘要：
随着视觉语言模型（VLMs）的快速发展，拒绝机制已成为确保负责任和安全模型行为的关键组成部分。然而，现有的拒绝策略大多是
英文摘要：
With the rapid advancement of Vision Language Models (VLMs), refusal mechanisms have become a critical component for ensuring responsible and safe model behavior. However, existing refusal strategies are largely \textit{one-size-fits-all} and fail to adapt to diverse user needs and contextual constraints, leading to either under-refusal or over-refusal. In this work, we firstly explore the challenges mentioned above and develop \textbf{C}onfigurable \textbf{R}efusal in \textbf{VLM}s (\textbf{CR-VLM}), a robust and efficient approach for {\em configurable} refusal based on activation steering. CR-VLM consists of three integrated components: (1) extracting a configurable refusal vector via a teacher-forced mechanism to amplify the refusal signal; (2) introducing a gating mechanism that mitigates over-refusal by preserving acceptance for in-scope queries; and (3) designing a counterfactual vision enhancement module that aligns visual representations with refusal requirements. Comprehensive experiments across multiple datasets and various VLMs demonstrate that CR-VLM achieves effective, efficient, and robust configurable refusals, offering a scalable path toward user-adaptive safety alignment in VLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
