No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Le, Thanh-Long V., Jeon, Myeongho, Vu, Kim, Lai, Viet, Yang, Eunho
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/2509.21880