Benchmarking Deception Probes via Black-to-White Performance Boosts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Parrack, Avi, Attubato, Carlo Leonardo, Heimersheim, Stefan
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning 68T01 I.2.7; K.4.1
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.12691