A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal
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…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
