Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Chengyu, Chou, Sheng-Yen, Zhang, Zhengxin, Cardie, Claire
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.20051