Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
- 2026-02-08
- 4
@misc{sun2026safety,
title = {Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection},
author = {Guang-Long Sun and Siyuan Zhang and Li-Yuan Wang and Jun Zhu and Hang Su and Yi Zhong},
year = {2026},
eprint = {2602.07892},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2602.07892},
}