Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nguyen, Phuc Minh, Nguyen, Ngoc-Hieu, Nguyen, Duy H. M., Liu, Anji, Mai, An, Nguyen, Binh T., Sonntag, Daniel, Doan, Khoa D.
Format:	Preprint
Published:	2025
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/2506.08681