2 papers
cs.CL2026
Lost in Delusion: Examining LLM Safety Under User Delusions and Distress
Andrew Aquilina, Chetna Nihalani, Vasudha Varadarajan +3
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 o…
cs.CL2026
Auditing Support Strategies in LLMs through Grounded Multi-Turn Social Simulation
Michelle Star, Andrew Aquilina, Yu-Ru Lin
When users seek social support from chatbots, they disclose their situation gradually, yet most evaluations of supportive LLMs rely on single-turn, fully specified prompts. We intr…