Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Lijun, Li, Lin, Wei, Wei, Qi, Yajie, Song, Huizhong, Wang, Jun, Yang, Yaodong, Liang, Jiye
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!