智能AI
None
当乐于助人变成阿谀奉承时：阿谀奉承是大型语言模型中社会一致性和认知完整性之间的边界失败
05403v1 Announce Type: new Abstract: This position paper argues that sycophancy in LLMs is a boundary failure between so
2026-05-09
Jiechen Li, Catherine A. Barry, Rishika Randev, Janet Chen, Ella Jorgensen, Brinnae Bent