Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tran, Thien Q., Wachi, Akifumi, Sato, Rei, Tanabe, Takumi, Akimoto, Youhei
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.02153