@inproceedings{li-etal-2026-llm,
    title = "Can {LLM} Safety Be Ensured by Constraining Parameter Regions?",
    author = "Li, Zongmin  and
      Su, Jian  and
      Benamara, Farah  and
      Sun, Aixin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1616/",
    pages = "34979--35011",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language models (LLMs) are often assumed to contain ``safety regions'' - parameter subsets whose modification directly influences safety behaviors. We conduct a systematic evaluation of four safety region identification methods spanning different parameter granularities, from individual weights to entire Transformer layers, across four families of backbone LLMs with varying sizes. Using ten safety identification datasets, we find that the identified safety regions exhibit only low to moderate overlap, as measured by IoU. The overlap drops significantly when the safety regions are further refined using utility datasets (i.e. non-harmful queries). These results suggest that current techniques fail to reliably identify a stable, dataset-agnostic safety region."
}