@inproceedings{chua-etal-2026-rock,
    title = "Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in {LLM}s",
    author = "Chua, Shei Pern  and
      Thai, Zhen Leng  and
      Teh, Kai Jun  and
      Li, Xiao  and
      Ren, Qibing  and
      Hu, Xiaolin",
    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.197/",
    pages = "4275--4310",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason through moral trade-offs creates a distinct attack surface. We formalize this vulnerability through TRIAL, a multi-turn red-teaming methodology that embeds harmful requests within ethical framings. TRIAL achieves consistently high attack success rates across models by exploiting the model{'}s own ethical reasoning to frame harmful actions as morally necessary compromises. Building on these insights, we introduce ERR (Ethical Reasoning Robustness), a defense framework that distinguishes between instrumental responses that enable harmful outcomes and explanatory responses that analyze ethical frameworks without endorsing harmful acts. ERR employs a Layer-Stratified Harm-Gated LoRA architecture, achieving robust defense against reasoning-based attacks while preserving model utility."
}