arXiv (All)
open access
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
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal#1006885
- In defence of gullibility: The epistemology of testimony and the psychology of deception detection#753454
- Geoffrey C. Bunn, The Truth Machine: A Social History of the Lie Detector. Baltimore: Johns Hopkins University Press, 2012. Pp. ix+246. ISBN 978-1-4214-0530-8. £18.00#743086
- Lying, risk and accuracy#734625
- 29 U.S.C. § 2002 — Prohibitions on lie detector use#583818
Record · ID 1036384
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive