AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Songming, Zhang, Xue, Zhang, Tong, Hu, Bojie, Chen, Yufeng, Xu, Jinan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.02832