Consistent Client Simulation for Motivational Interviewing-based Counseling

2025-02-05

AI Summary

To address the inconsistency between virtual client behaviors and predefined psychological traits in Motivational Interviewing (MI) simulations, this paper proposes the first controllable client simulation framework integrating psychological state trajectory modeling with explicit consistency constraints. Methodologically, we construct a structured psychological state ontology to model the dynamic evolution of motivation, beliefs, readiness for change, and openness to suggestions; we further design a state-aware prompting mechanism and a multi-dimensional behavioral constraint generator to ensure strict adherence to role specifications. Our key contribution lies in explicitly incorporating psychological process modeling into conversational simulation, enabling configurable, high-fidelity client generation across diverse MI scenarios. Automated evaluation and expert assessment demonstrate that our approach significantly outperforms existing baselines in behavioral consistency, role credibility, and cross-scenario stability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Simulating human clients in counseling
• Ensuring consistent client behaviors
• Tracking mental state transitions effectively

Innovation

• Mental state tracking method
• Behavior generation algorithm
• Consistent simulation framework