Search

What are you looking for?

1 result for llm-safety

AI·Across five instruction-tuned LLMs, ordinary answer-confidence separates correct from wrong answers on answerable questions but fails to distinguish unanswerable questions (e.g., false-premise ones in CREPE), while a linear probe on hidden states performs the opposite, revealing two distinct abstention axes that remain separable even at 14B scale.

arXiv cs.CL·arxiv.org··1.8Researchllmabstentionllm-safety