Self-Reflection Makes Large Language Models Safer, Less Biased, and Ideologically Neutral

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Fengyuan, AlDahoul, Nouar, Eady, Gregory, Zaki, Yasir, Rahwan, Talal
Format:	Preprint
Published:	2024
Subjects:	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/2406.10400