ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiaomin, Chen, Xupeng, Fan, Jingxuan, Jiang, Eric Hanchen, Gao, Mingye
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!