English

Virtual Agents for Alcohol Use Counseling: Exploring LLM-Powered Motivational Interviewing

Human-Computer Interaction 2024-07-12 v1 Computation and Language

Abstract

We introduce a novel application of large language models (LLMs) in developing a virtual counselor capable of conducting motivational interviewing (MI) for alcohol use counseling. Access to effective counseling remains limited, particularly for substance abuse, and virtual agents offer a promising solution by leveraging LLM capabilities to simulate nuanced communication techniques inherent in MI. Our approach combines prompt engineering and integration into a user-friendly virtual platform to facilitate realistic, empathetic interactions. We evaluate the effectiveness of our virtual agent through a series of studies focusing on replicating MI techniques and human counselor dialog. Initial findings suggest that our LLM-powered virtual agent matches human counselors' empathetic and adaptive conversational skills, presenting a significant step forward in virtual health counseling and providing insights into the design and implementation of LLM-based therapeutic interactions.

Keywords

Cite

@article{arxiv.2407.08095,
  title  = {Virtual Agents for Alcohol Use Counseling: Exploring LLM-Powered Motivational Interviewing},
  author = {Ian Steenstra and Farnaz Nouraei and Mehdi Arjmand and Timothy W. Bickmore},
  journal= {arXiv preprint arXiv:2407.08095},
  year   = {2024}
}
R2 v1 2026-06-28T17:36:35.223Z