Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Wenkai, Shen, Shiqi, Shen, Guangyao, Yao, Wei, Liu, Yong, Gong, Zhi, Lin, Yankai, Wen, Ji-Rong
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2406.11431