Truth probes follow the persona, but the answer doesn't go through them
I am fairly confident about the effect for a range of models (at least 4 model families). I am less certain about the mechanism and results are only for linear probes.Reason for BeliefIf a model has a "truth" direction along which its representations vary with whether it believes a statement to be true, this may provide a useful mechanism for lie detection. However, this assumes the generated answer will also be impacted by the truth value, and this has rarely been checked. Models, given a perso...
Read full article →