@inproceedings{eshuijs-etal-2026-safety,
    title = "Safety Training Modulates Harmful Misalignment Under On-Policy {RL}, But Direction Depends on Environment Design",
    author = "Eshuijs, Leon  and
      Wang, Shihan  and
      Fokkens, Antske",
    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.2461/",
    doi = "10.18653/2026.emnlp-main.2461",
    pages = "55879--55908",
    ISBN = "979-8-89176-459-0"
}