Refusal Is Not Robustness: Auditing Confident Fabrication in Large Language Models on a Provably Uninformative Clinical Pain Speech Transcript

arXiv cs.AIAugust 28, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2608.26167v1 Announce Type: new Abstract: Hallucination and abstention benchmarks rarely establish that a model could not have known the correct answer, making it difficult to distinguish appropriate abstention from an unsupported prediction. Seven large language models were evaluated on the TAME Pain speech corpus. Participants read phonetically balanced Harvard Sentences while one hand was immersed in cold or warm water and reported pain only during periodic pain statements. This protocol generated 5,750 no signal Harvard Sentence utterances whose transcripts contained no lexical pain information and 1,294 signal pain statement utterances in which the pain rating was explicitly spoke

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Verktyg
• Forskning