AI RESEARCH
Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
arXiv CS.LG
•
ArXi:2605.21006v1 Announce Type: cross We study the effect of different persona on \textbf{sycophancy}: model's agreement with users even when the user is incorrect. The standard mitigation, Contrastive Activation Addition (CAA), derives a steering direction from labelled pairs of sycophantic and honest responses. This study evaluates whether off-the-shelf persona steering vectors, originally developed for general role-playing and not trained on sycophancy data, can serve as an alternative.