PsyProbe: Proactive and Interpretable Dialogue through User State Modeling for Exploratory Counseling

2026-01-27

AI Summary

This work addresses the limitation of existing mental health dialogue systems, which are predominantly reactive and lack the ability to actively model and explore users’ psychological states. The authors propose PsyProbe, a system that constructs a structured representation of psychological states during the exploratory phase of counseling by integrating the PPPPPI psychological framework with cognitive distortion detection. PsyProbe further incorporates a memory mechanism, strategic planning, and a generative module featuring question ideation and critical revision to enable proactive and interpretable question generation. Notably, this study is the first to combine structured psychological state modeling with motivational interviewing behavior coding, significantly enhancing understanding of core issues and user engagement. In experiments with 27 real users, PsyProbe outperformed baseline and ablation models across automatic, user, and expert evaluations, achieving question quality comparable to that of professional counselors and markedly improving dialogue naturalness and user willingness to engage.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Recent advances in large language models have enabled mental health dialogue systems, yet existing approaches remain predominantly reactive, lacking systematic user state modeling for proactive therapeutic exploration. We introduce PsyProbe, a dialogue system designed for the exploration phase of counseling that systematically tracks user psychological states through the PPPPPI framework (Presenting, Predisposing, Precipitating, Perpetuating, Protective, Impact) augmented with cognitive error detection. PsyProbe combines State Builder for extracting structured psychological profiles, Memory Construction for tracking information gaps, Strategy Planner for Motivational Interviewing behavioral codes, and Response Generator with Question Ideation and Critic/Revision modules to generate contextually appropriate, proactive questions. We evaluate PsyProbe with 27 participants in real-world Korean counseling scenarios, including automatic evaluation across ablation modes, user evaluation, and expert evaluation by a certified counselor. The full PsyProbe model consistently outperforms baseline and ablation modes in automatic evaluation. User evaluation demonstrates significantly increased engagement intention and improved naturalness compared to baseline. Expert evaluation shows that PsyProbe substantially improves core issue understanding and achieves question rates comparable to professional counselors, validating the effectiveness of systematic state modeling and proactive questioning for therapeutic exploration.

Problem

• proactive dialogue
• user state modeling
• exploratory counseling
• mental health dialogue systems
• therapeutic exploration

Innovation

• user state modeling
• proactive questioning
• PPPPPI framework
• Motivational Interviewing
• cognitive error detection