@article{waldis-etal-2026-aligned,
    title = "Aligned Probing: Relating Toxic Behavior and Model Internals",
    author = "Waldis, Andreas  and
      Gautam, Vagrant  and
      Lauscher, Anne  and
      Klakow, Dietrich  and
      Gurevych, Iryna",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "14",
    year = "2026",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/ingest-latest-mitpress-cl-tacl/2026.tacl-1.14/",
    doi = "10.1162/tacl.a.613",
    pages = "271--291"
}