Consistent Client Simulation for Motivational Interviewing-based Counseling

TL;DR

This paper introduces a novel framework for simulating consistent mental health counseling clients, enabling scalable training and evaluation of counselors by maintaining realistic, profile-driven interactions.

Contribution

It presents a new method that tracks mental states and controls state transitions to generate consistent client behaviors in counseling simulations.

Findings

Achieves higher consistency than previous methods

Effectively varies client profiles and receptivity

Supports scalable mental health counseling training

Abstract

Simulating human clients in mental health counseling is crucial for training and evaluating counselors (both human or simulated) in a scalable manner. Nevertheless, past research on client simulation did not focus on complex conversation tasks such as mental health counseling. In these tasks, the challenge is to ensure that the client's actions (i.e., interactions with the counselor) are consistent with with its stipulated profiles and negative behavior settings. In this paper, we propose a novel framework that supports consistent client simulation for mental health counseling. Our framework tracks the mental state of a simulated client, controls its state transitions, and generates for each state behaviors consistent with the client's motivation, beliefs, preferred plan to change, and receptivity. By varying the client profile and receptivity, we demonstrate that consistent simulated clients for different counseling scenarios can be effectively created. Both our automatic and expert evaluations on the generated counseling sessions also show that our client simulation method achieves higher consistency than previous methods.