Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs 事件

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs arXiv:2509.05367v5 Announce Type: replace-cross 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,