Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
arXiv AIArchived May 22, 2026✓ Full text saved
arXiv:2605.21006v1 Announce Type: new Abstract: 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 alternat
Full text archived locally
✦ AI Summary· Claude Sonnet
Computer Science > Artificial Intelligence
[Submitted on 20 May 2026]
Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
Ishaan Kelkar, Nebras Alam, Vikram Kakaria, Madhur Panwar, Vasu Sharma, Maheep Chaudhary
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. In two instruction-tuned models, steering toward personas characterised by doubt or scrutiny reduces sycophancy to approximately 68\% and 98\% of CAA's effect, and, unlike CAA, maintains accuracy when the user is correct. The effect is also asymmetric: steering toward agreeable personas does not produce a mirror increase in sycophancy. Geometrically, the persona vector is largely independent of the direction of sycophancy in activation space. Collectively, these findings suggest that sycophancy is better understood as a persona-level property rather than a single steerable direction. We release our code here: this https URL.
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
Cite as: arXiv:2605.21006 [cs.AI]
(or arXiv:2605.21006v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.21006
Focus to learn more
Submission history
From: Maheep Chaudhary [view email]
[v1] Wed, 20 May 2026 10:43:17 UTC (189 KB)
Access Paper:
HTML (experimental)
view license
Current browse context:
cs.AI
< prev | next >
new | recent | 2026-05
Change to browse by:
cs
cs.CL
cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Export BibTeX Citation
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Demos
Related Papers
About arXivLabs
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)