Evaluating Language Model Responses to Mental Health Symptom Disclosures
by Micah Benson
Survey of Predictive Recursive Algorithms for Inference
by Clark Ikezu
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.
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. He uses interpretability methods to investigate how LLMs represent social concepts such as identity and politics, with the goal of developing techniques to improve model fairness. He also conducts audits that simulate new uses of LLMs to analyze potential benefits and risks of the technology. Before BU, Micah graduated from WashU with a double major in data science and English.
Clark Ikezu
Clark is a second-year PhD student at Boston University's Faculty of Computing and Data Sciences. He is broadly interested in understanding biological systems and 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.