The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Springer, Max, Lee, Chung Peng, Metevier, Blossom, Castleman, Jane, Turbal, Bohdan, Jung, Hayoung, Shen, Zeyu, Korolova, Aleksandra
Format:	Preprint
Published:	2026
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/2602.15799