MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xie, Shuo, Zhu, Fangzhi, Wang, Jiahui, Wen, Lulu, Dai, Wei, Chen, Xiaowei, Zhu, Junxiong, Zhou, Kai, Zheng, Bo
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.15244