4 stories tagged with #sycophancy, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Sycophancy"
RELATED TAGS
ARXIV.ORG
Detecting and Controlling Sycophancy with Cascading Linear Features
arXiv:2606.26155v1 Announce Type: new Abstract: Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples that cle…
ARXIV CS.AI
Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
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 Addit…
R/PROMPTENGINEERING
Please write a prompt to minimize sycophancy, taking sides, flattering, echo-chamber, "yes-man", assumptions, and improve objectivity, brutal honesty, neutrality, and real-world verity.
R/PROMPTENGINEERING