Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Mengxuan, Datla, Vivek V., Kumar, Anoop, Guan, Zihan, Li, Sheng, Samuel, Alfy, Liu, Daben
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.21346