Factored Causal Representation Learning for Robust Reward Modeling in RLHF

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yupei, Yang, Lin, Deng, Wanxi, Qu, Lin, Feng, Fan, Huang, Biwei, Tu, Shikui, Xu, Lei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!