Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Fanfan, Yin, Youyang, Shi, Peng, Yang, Siqi, Zeng, Zhixiong, Qiu, Haibo
Format:	Preprint
Published:	2026
Subjects:	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/2602.05261