Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lai, Xin, Tian, Zhuotao, Chen, Yukang, Yang, Senqiao, Peng, Xiangru, Jia, Jiaya
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence 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/2406.18629