@article{safetyalignmentshouldbemademorethan, title = {Safety Alignment Should Be Made More Than Just a Few Tokens Deep}, author = {Xiangyu Qi and Ashwinee Panda and Kaifeng Lyu and Xiao Ma and Subhrajit Roy and Ahmad Beirami and Prateek Mittal and Peter Henderson}, year = {2024}, eprint = {2406.05946}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.05946v1}, }