Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Zimu, Zhou, Aojun, Wang, Ke, Ren, Houxing, Shi, Weikang, Pan, Junting, Zhan, Mingjie, Li, Hongsheng
Format:	Preprint
Published:	2024
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/2407.00782