Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kezins, Nikita, Ekka, Urbas, Berrang, Pascal, Arnaboldi, Luca
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.10901