SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yi, Hao, Li, Qingyang, Hu, Yulan, Zhang, Fuzheng, Zhang, Di, Liu, Yong
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.13516