MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qi, Yupeng, Lyu, Ziyu, Yang, Min, Wang, Yanlin, Bai, Lu, Cui, Lixin
Format:	Preprint
Published:	2025
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/2506.02460