首页 > AI前沿 > Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibratione

Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibratione

arXiv自然语言 2026-09-06 17:37 4 阅读 查看原文

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.