Off-the-shelf persona vectors for doubt and scrutiny reduce sycophancy comparably to CAA while maintaining accuracy on correct inputs and showing directional independence.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
Off-the-shelf persona vectors for doubt and scrutiny reduce sycophancy comparably to CAA while maintaining accuracy on correct inputs and showing directional independence.