10 papers
Reliability Auditing for Downstream LLM tasks in Psychiatry: LLM-Generated Hospitalization Risk Scores
Shevya Panda, Shinjini Bose, Ananya Joshi
Large language models (LLMs) are increasingly utilized in clinical reasoning and risk assessment. However, their interpretive reliability in critical and indeterminate domains such…
Context-Aware Hospitalization Forecasting Evaluations for Decision Support using LLMs
Rhea Makkuni, Ananya Joshi
Medical and public health experts must make real-time resource decisions, such as expanding hospital bed capacity, based on projected hospitalization trends during large-scale heal…
Optimal Question Selection from a Large Question Bank for Clinical Field Recovery in Conversational Psychiatric Intake
Guan Gui, Peter Zandi, Jacob Taylor +1
Psychiatric intake is a sequential, high-stakes information-gathering process in which clinicians must decide what to ask, in what order, and how to interpret incomplete or ambiguo…
Reliable Self-Harm Risk Screening via Adaptive Multi-Agent LLM Systems
Meghana Karnam, Ananya Joshi
Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, c…
Constrained Process Maps for Multi-Agent Generative AI Workflows
Ananya Joshi, Michael Rudow
Large language model (LLM)-based agents are increasingly used to perform complex, multi-step workflows in regulated settings such as compliance and due diligence. However, many age…
Decomposing Theory of Mind: How Emotional Processing Mediates ToM Abilities in LLMs
Ivan Chulo, Ananya Joshi
Recent work shows activation steering substantially improves language models' Theory of Mind (ToM) (Bortoletto et al. 2024), yet the mechanisms of what changes occur internally tha…