SOURCE-LINKED INTELLIGENCE

LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Safety guardrails serve as the last line of defense against harmful inputs and outputs of large language models (LLMs), yet they are trained and evaluated almost exclusively on short text. We present LongGuard, a framework that evaluates, mechanistically analyzes, and mitigates long-context guardrail failure. We formulate the task as Safety Needle-in-a-Haystack (SafetyNIAH) over a 0.25k-32k length grid; across 15 mainstream guardrails, unsafe recall drops monotonically by more than 50% on average, and a paired Benign-Fill vs. Needle-Repeat design attributes the failure to proportional dilution

Read original source ↗ Open in workspace

recordType

paper

region

Global