משחק את השטן: וקטורי פרסונה מסחררים כמעט כמו ניהול מומחה למניעת סיקופנטיות

תקציר מקורי באנגליתarXiv:2605.21006v3 Announce Type: replace Abstract: Sycophancy is the tendency of language models to agree with users irrespective of correctness. Prior work has extracted sycophancy persona vectors and causally controlled this trait through activation steering (Chen et al., 2025; arXiv:2507.21509). We ask whether existing vectors for general roles, extracted without targeting sycophancy, transfer to this mitigation task. We compare critical and conformist role vectors with a sycophancy-targeted Contrastive Activation Addition (CAA) baseline on a held-out, counterbalanced PhilPapers benchmark, using task-specific coefficient tuning. On Gemma 2 27B and Qwen 3 32B, the selected critical-role vectors achieve mean sycophancy-logit reductions approximately 68% and 98% as large as CAA's, respect