A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dobre, David, Mofakhami, Mehrnaz, Xhonneux, Sophie, Schwinn, Leo, Gidel, Gauthier
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.16366