CoRPO: Adding a Correctness Bias to GRPO Improves Generalization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Garg, Anisha, Zhang, Claire, Neema, Nishit, Bick, David, Venkatesh, Ganesh, Hestness, Joel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!