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 reveal whether it is hiding an answer or simply does not have one.

PIR borrows the Concealed Information Test, a forensic method that identifies guilty knowledge by presenting a suspect with the true detail among plausible decoys and measuring a stronger response to the item they recognize. The method does the same inside a model: it presents a question with its candidate answers and reads from the model's internal states which candidate the model recognizes as correct. PIR is reference-free, requiring no honest reference model and no labeled truth corpus.

Across eight models from five families (Gemma, Qwen, Llama, Mistral, and Phi), PIR recovers the recognized answer at 0.70 to 0.87 balanced accuracy, well above the 0.28 to 0.40 unknown-item baseline and the 0.25 chance rate. It stays readable across every form of concealment tested, including prompted deception, trained sandbagging, and external password-locked and circuit-broken checkpoints, with recognition between 0.85 and 0.93. When the model hides a known answer, recognition stays high, but when unlearning removes the knowledge, recognition drops to the level of a question the model never knew.

PIR therefore separates a model that will not answer from one that cannot, which supports sandbagging audits and unlearning verification. The signal is causal, adds information beyond black-box behavioral cues, and extends from multiple-choice questions to free-form generation.