Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cao, Chentao, Xu, Xiaojun, Han, Bo, Li, Hang
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.11629