On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Williams, Marcus, Carroll, Micah, Narang, Adhyyan, Weisser, Constantin, Murphy, Brendan, Dragan, Anca
Format:	Preprint
Published:	2024
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/2411.02306