Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zeng, Xia, Chen, Yihan, Liu, Luhui, Luo, Chao, Chen, Ye, Zhuang, Zhuoran
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/2510.04214