Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tan, Daniel, Woodruff, Anders, Warncke, Niels, Jose, Arun, Riché, Maxime, Africa, David Demitri, Taylor, Mia
Format:	Preprint
Published:	2025
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/2510.04340