Building Closed-Loop LLM Systems for Scalable Mental Health Support on 4 March 2026: Seminar
Abstract
Mental health systems worldwide are under growing strain, with increasing demand for early support and limited specialist capacity. While large language models (LLMs) have shown promise in conversational mental health applications, most existing systems operate as static chatbots without structured assessment, longitudinal monitoring, or calibrated escalation mechanisms. This talk presents a closed-loop LLM framework designed to support scalable mental health care rather than isolated conversational assistance. The system integrates empathetic dialogue generation with continuous state assessment, structured rubric-based evaluation, and reinforcement-driven improvement. A multi-agent architecture enables iterative feedback between support generation and risk evaluation, forming a dynamic loop that mirrors stepped-care principles in public health.
About the speaker
Dr. He Kai is a postdoctoral researcher at the National University of Singapore, School of Public Health, specializing in medical artificial intelligence and large language models for healthcare. His research focuses on building scalable and trustworthy AI systems for real-world healthcare applications, particularly in mental health support and clinical decision-making. Dr. He has led translational AI projects in collaboration with national agencies such as the Singapore Civil Defence Force, developing intelligent triage systems that have been deployed in practice. His work has received institutional and national recognition and has been featured at major healthcare innovation events. In addition to his research, he serves as an Associate Editor for IEEE Transactions on Affective Computing and Health Data.
.jpg?sfvrsn=bb2daf73_3)
.tmb-listing.jpg?Culture=en&sfvrsn=6518a5d2_1)
