AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lindström, Adam Dahlgren, Methnani, Leila, Krause, Lea, Ericson, Petter, de Troya, Íñigo Martínez de Rituerto, Mollo, Dimitri Coelho, Dobbe, Roel
Format:	Preprint
Published:	2024
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2406.18346