משחק עם השטן: וקטורי דמות רכשיים חוקרים ניהול חסות

תקציר מקורי באנגליתarXiv:2605.21006v4 Announce Type: replace Abstract: Language models are often sycophantic: they agree with a user's stated opinion whether or not it is correct. Prior work has shown that this trait can be controlled by steering a model with a sycophancy persona vector (Chen et al., 2025). Such vectors, however, are extracted from data about sycophancy itself. We ask whether we can instead reuse existing vectors for general roles---Skeptic, Judge, Devil's Advocate---that were extracted without targeting sycophancy at all. On Gemma 2 27B and Qwen 3 32B, we compare these role vectors with a purpose-built Contrastive Activation Addition (CAA) sycophancy vector on a largely held-out, counterbalanced PhilPapers benchmark, using task-specific coefficient tuning on a separate split of sycophancy d