SOURCE-LINKED INTELLIGENCE

Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models

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

Safety alignment teaches large language models (LLMs) to recognize harmful requests and reject risky instructions. Yet aligned models can fail when harmful intent is concealed within seemingly benign contexts. Robust safety therefore requires both knowledge of safety boundaries and \textbf{vigilance}: the ability to detect unusual premises, misleading reasoning, and latent risks beneath surface-level semantics. Vigilance requires models to scrutinize a request's underlying intent and assumptions before acting. To cultivate this capability, we introduce \textbf{cunning questions}, which are not

Read original source ↗ Open in workspace

recordType

paper

region

Global