一作NeurIPS 2026Poster
From Preference Data to Personalization: Tracing Sycophancy in Large Language Models
Claudia Shi · Himaghna Bhattacharjee · Yasha Sheynin · Shivam Singhal · Ankur Samanta · Arjun Subramonian · Julian Michael · Maximilian Nickel · Smitha Milli
对齐与偏好OpenReview