@inproceedings{vetter-etal-2026-data,
    title = "Data Attribution of Emergent Misalignment with Persona Features",
    author = "Vetter, Clemens  and
      Kacz{\'e}r, David  and
      Flek, Lucie  and
      Mai, Florian",
    editor = "Arad, Dana  and
      Belinkov, Yonatan  and
      Chen, Hanjie  and
      Feldhus, Nils  and
      Mueller, Aaron  and
      Mohebbi, Hosein  and
      Sarti, Gabriele  and
      Tutek, Martin",
    booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.blackboxnlp-1.10/",
    pages = "136--165",
    ISBN = "979-8-89176-476-7"
}