@inproceedings{nguyen-etal-2026-beyond-shallow,
    title = "Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness",
    author = "Nguyen, Hoang Cuong  and
      Dras, Mark  and
      Naseem, Usman",
    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.2057/",
    pages = "46834--46860",
    ISBN = "979-8-89176-459-0"
}