ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Yang, Zhang, Huayi, Jiao, Yizheng, Ma, Lin, Liu, Xiaozhong, Yu, Jinhong, Zhang, Dongyu, Yu, Dezhi, Xu, Wei
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence 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/2412.00631