Truth-direction probes generalize across short conversational formats that end on a lie but fail on longer formats where the lie appears earlier, and a fixed key phrase at the end of the prompt substantially improves this generalization.
Large language models can strategi- cally deceive their users when put under pressure
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring the generalization of LLM truth directions on conversational formats
Truth-direction probes generalize across short conversational formats that end on a lie but fail on longer formats where the lie appears earlier, and a fixed key phrase at the end of the prompt substantially improves this generalization.