Lost in Delusion: Examining LLM Safety Under User Delusions and Distress 事件

Lost in Delusion: Examining LLM Safety Under User Delusions and Distress arXiv:2606.00975v1 Announce Type: new Abstract: LLM chatbots increasingly serve as a first source of support for people in psychological distress, including those whose distress is entangled with delusional beliefs. Prior work on LLM mental-health safety largely evaluates general therapeutic quality or single-turn crisis detection, leaving unclear how models behave when distress is intertwined with delusion over sustained