CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Exploration

TL;DR

CAMI is an innovative AI counselor agent that uses state inference and topic exploration to deliver motivational interviewing, improving counseling effectiveness and realism through large language models.

Contribution

This paper introduces CAMI, a novel counselor agent based on the STAR framework that integrates state inference and topic exploration for MI support using LLMs.

Findings

CAMI outperforms existing methods in MI skill competency.

CAMI demonstrates more realistic counselor-like behavior.

Ablation studies confirm the importance of state inference and topic exploration.

Abstract

Conversational counselor agents have become essential tools for addressing the rising demand for scalable and accessible mental health support. This paper introduces CAMI, a novel automated counselor agent grounded in Motivational Interviewing (MI) -- a client-centered counseling approach designed to address ambivalence and facilitate behavior change. CAMI employs a novel STAR framework, consisting of client's state inference, motivation topic exploration, and response generation modules, leveraging large language models (LLMs). These components work together to evoke change talk, aligning with MI principles and improving counseling outcomes for clients from diverse backgrounds. We evaluate CAMI's performance through both automated and manual evaluations, utilizing simulated clients to assess MI skill competency, client's state inference accuracy, topic exploration proficiency, and overall counseling success. Results show that CAMI not only outperforms several state-of-the-art methods but also shows more realistic counselor-like behavior. Additionally, our ablation study underscores the critical roles of state inference and topic exploration in achieving this performance.