Robust Post-Training for Generative Recommenders: Why Exponential Reward-Weighted SFT Outperforms RLHF

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chidambaram, Keertana, Krishnamurthy, Sanath Kumar, Xu, Qiuling, Hsiao, Ko-Jen, Bhattacharya, Moumita
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.10279