Evaluating Language Model Responses to Mental Health Symptom Disclosures
by Micah Benson
Survey of Predictive Recursive Algorithms for Inference
by Clark Ikezu
About
Micah: We use depression and anxiety questionairres to build an evaluation dataset that simulates mental health symptoms disclosures by language model users. We analyze patterns in language model responses and explore how common jailbreaks change these behaviors.
Clark: There has been growing interest in Bayesian predictive inference. This talk will survey predictive recursive algorithms and other related stochastic approximation algorithms for inferring quantities of interest given noisy, (possibly partially) exchangeable observations from some unknown, underlying system.
Details
- Date:
- Friday, April 10, 2026
- Time:
- 12:00 PM - 1:00 PM
- Location:
- CDS 1646
- Theme:
- AI, Computational Methodology
Speakers
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.
Clark Ikezu
Clark is a third-year PhD student at Boston University's Faculty of Computing and Data Sciences. He is broadly interested in understanding spatiotemporal processes with statistical modeling. Previously he worked at the Mayo Clinic at Jacksonville, FL, and before that earned a Master of Science in Bioengineering from Stanford University and a Bachelor of Science from Boston University in Biomedical Engineering.