Mind the Gap: Data Rewriting for Stable Off-Policy Supervised Fine-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Shiwan, Zhao, Xuyang, Zhou, Jiaming, Kong, Aobo, Li, Qicheng, Qin, Yong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.15157