Empathic Dialog Systems for Patient Intake: Balancing Task-Completion and Emotional Support using RAGs

Dialogue systems are increasingly recognized as valuable assets in healthcare, aiding in the support of individuals grappling with mental health challenges. In this paper, we develop and evaluate a task-oriented empathic chatbot, EmoBot, in a mental healthcare patient intake scenario. EmoBot employs Retrieval-Augmented Generation (RAG) methods to provide guardrails to Large Language Models (LLMs) in providing targeted empathic support, while ensuring task-completion of administering PHQ-9 intake questionnaire. We evaluate EmoBot’s performance by using a simulated patient model to mimic varying levels of depression severity. Our preliminary results showed high task completion rates and agreement between EmoBot’s depression severity categorization and human raters, demonstrating the promise of RAG-based methods in guiding LLMs to be used for health assessment and support.