Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Kumar, Sachin
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning I.2.7; I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.27958