SOURCE-LINKED INTELLIGENCE

First Token Matters: Understanding Safety Collapse in Large Reasoning Models

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Large Reasoning Models (LRMs) exhibit strong problem-solving abilities, yet their safety alignment often degrades when handling harmful queries. Existing approaches to improving safety largely rely on additional training or preference optimization, while offering limited understanding of the internal mechanisms behind safety failures. In this work, we investigate this failure through a token-level positional analysis of refusal dynamics and identify a localized vulnerability at the onset of reasoning, which we term Onset Refusal Collapse (ORC). We find that the refusal-related signal of LRMs d

Read original source ↗ Open in workspace

recordType

paper

region

Global