Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Wei, Wu, Yubing, Yang, Junmei, Zeng, Delu, Zhao, Qibin, Paisley, John, Chen, Min, Wang, Zhou
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!