Preference Poisoning Attacks on Reward Model Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Junlin, Wang, Jiongxiao, Xiao, Chaowei, Wang, Chenguang, Zhang, Ning, Vorobeychik, Yevgeniy
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/2402.01920