Paper recorded by Signals 4 on 2026-09-18 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-18 on arXiv · recorded by Signals 4 on 2026-09-21
Category: cs.AI · 人工智能 · first seen 2026-09-21
Large language models can hold knowledge they do not report. A model may sandbag on a capability evaluation, or answer against what it internally knows, and its outputs alone cannot tell whether it is hiding an answer or simply does not have one. We borrow the Concealed Information Test, a forensic method that identifies guilty knowledge by presenting a suspect with the true detail among plausible