通过动态语义路由校准缓解大语言模型的过度拒绝问题
Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration
- School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）
- CSIRO（澳大利亚联邦科学与工业研究组织）
- Center of Excellence for Generative AI, King Abdullah University of Science and Technology（阿卜杜拉国王科技大学生成式人工智能卓越中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出语义路由校准（SRC），一种轻量级、无需训练的推理框架，通过动态抑制超敏感安全头并融合双分支逻辑，缓解大语言模型对良性安全相关指令的过度拒绝，同时保持安全性能。
AI中文摘要：
为安全而对齐的大语言模型（LLMs）常常遭受过度拒绝的问题，即错误地拒绝良性但涉及安全的指令。先前的研究主要将此归因于静态表示重叠，在很大程度上忽视了潜在的动态机制。在本文中，我们通过变压器注意力内部的动态路由冲突视角，对过度拒绝进行了机制性分析。我们发现，一个稀疏的“超敏感安全头”子集在“硬安全”提示上会误触发，表现出异常的注意力纠缠，将无害的目标实体强行绑定到拒绝语义上。这引发了一个严重的、高熵的路由冲突，剥夺了目标实体所需的注意力。为应对这一问题，我们提出了语义路由校准（SRC），一个轻量级、无需训练的推理框架。SRC在推理阶段精确定位并动态抑制这些超敏感的安全头。结合作为后续解码过程中安全正则化器的双分支逻辑融合，SRC无缝地恢复了可信的推理。大量实验表明，SRC缓解了过度拒绝，同时尽可能保留了内在的安全性能。
英文摘要：
Large language models (LLMs) aligned for safety often suffer from over-refusal, incorrectly rejecting benign yet safety-related instructions. Prior studies primarily attribute this to static representation overlap, largely overlooking the underlying dynamic mechanisms. In this paper, we present the mechanistic analysis of over-refusal through the lens of internal routing conflicts within transformer attention. We discover that a sparse subset of Hypersensitive Safety Heads misfires on Hard-Safe prompts, exhibiting abnormal attention entanglement that forcefully binds harmless target entities to refusal semantics. This triggers a severe, high-entropy routing conflict that deprives target entities of necessary attention. To counteract this, we propose Semantic Routing Calibration (SRC), a lightweight, training-free inference framework. SRC precisely localizes and dynamically suppresses these hypersensitive safety heads at the inference stage. Coupled with a dual-branch logits fusion that acts as a safety regularizer during subsequent decoding, SRC seamlessly restores trustworthy reasoning. Extensive experiments demonstrate that SRC alleviates over-refusal, with intrinsic safety performance preserved as much as feasible.
