Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Honglin, Hao, Qianyue, Xu, Fengli, Li, Yong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.21044