CALM-IT: Enhancing Synthetic Motivational Interviewing Dialogue Quality with Conversational Dynamics
CALM-IT is a dual-agent framework that explicitly tracks evolving client states and therapist inferences, such as rapport and goals, to guide dialogue generation. It outperformed existing methods by achieving the highest MITI ratings across various lengths and showed minimal quality degradation in long conversations. This suggests modeling conversational dynamics significantly improves the quality of synthetic therapeutic interactions.