WinoReferral: A Benchmark to Evaluate LLM Responses to Prompts Implying Mental Health Disorders
About
The use of LLMs has contributed to serious mental health conditions among a subset of users, most alarmingly cases of delusional thinking and suicide. My talk will begin by surveying leading theories from psychology and human computer interaction that explain how LLM use interacts with user mental health. I will then present my research on evaluating LLM responses to prompts that imply a user has depression and discuss our current results, which indicate high variance in AI companies’ safety policies for referring users to mental health professionals. I will conclude by proposing policy changes that could limit the harms of LLMs on user mental health.
Details
- Date:
- Friday, December 5, 2025
- Time:
- 12:00 PM - 1:00 PM
- Location:
- CDS 1646
- Theme:
- AI
Speaker
Micah Benson
Micah studies the societal impacts of large language models (LLMs) as a PhD Student at Boston University's Faculty of Computing & Data Sciences. His current research seeks to understand the psychological harms of conversational AI use. He evaluates how LLMs respond to users who disclose mental health symptoms, with the goal of characterizing patterns in these responses and proposing policy changes that would make the models safer for vulnerable users. Before BU, Micah graduated from WashU with a double major in data science and English.