@inproceedings{hazra-etal-2024-safety,
    title = "Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations",
    author = "Hazra, Rima  and
      Layek, Sayan  and
      Banerjee, Somnath  and
      Poria, Soujanya",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2024.emnlp-main.1212/",
    doi = "10.18653/v1/2024.emnlp-main.1212",
    pages = "21759--21776"
}