@inproceedings{ding-etal-2026-reins,
    title = "{REINS}: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features",
    author = "Ding, Kai-Xuan  and
      Xu, Hao-Xiang  and
      Peng, Ji-Hua  and
      Chen, Zi-Qi  and
      Wang, Jiaqi  and
      Ling, Zhen-Hua",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1298/",
    pages = "29541--29574",
    ISBN = "979-8-89176-459-0"
}