Chain-of-Interaction: Enhancing Large Language Models for Psychiatric Behavior Understanding by Dyadic Contexts

arXiv:2403.13786v1 Announce Type: new
Abstract: Automatic coding patient behaviors is essential to support decision making for psychotherapists during the motivational interviewing (MI), a collaborative communication intervention approach to address psychiatric issues, such as alcohol and drug addiction. While the behavior coding task has rapidly adapted machine learning to predict patient states during the MI sessions, lacking of domain-specific knowledge and overlooking patient-therapist interactions are major challenges in developing and deploying those models in real practice. To encounter those challenges, we …

abstract addiction alcohol arxiv behavior coding collaborative communication cs.cl decision decision making interviewing language language models large language large language models machine machine learning making patient support type understanding