Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Weixu, Yuan, Ye, Han, Changjiang, Tian, Yuxing, Sun, Zipeng, Du, Linfeng, Kang, Jikun, Kang, Hong, Liu, Xue, Wu, Haolun
Format:	Preprint
Published:	2026
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/2604.22345