Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bharadwaj, Anirudh, Malaviya, Chaitanya, Joshi, Nitish, Yatskar, Mark
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.05339