Removing Sandbagging in LLMs by Training with Weak Supervision

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ryd, Emil, Bartsch, Henning, Stastny, Julian, Benton, Joe, Hebbar, Vivek
Format:	Preprint
Published:	2026
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/2604.22082