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

TL;DR

The paper tackles the limitation of reactive, state-agnostic counseling by introducing PsyProbe, a proactive dialogue system that models user psychological states with the PPPPPI framework augmented by cognitive-error signals. Its four-module architecture—State Builder, Memory Construction, Strategy Planner, and Response Generator—enables MI-informed planning and context-grounded proactive questioning during exploration. In real Korean counseling scenarios with 27 participants, PsyProbe outperforms GPT-based baselines on automatic metrics and substantially boosts engagement and core-issue understanding, approaching human counselor performance in probing quality and question rate. While empathy remains an area for improvement, the results validate the value of explicit state modeling and proactive questioning for therapeutic exploration, with implications for scalable, patient-centered mental health support using LLMs.

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.

Figures (3)

• Figure 1: Overview of the PsyProbe system architecture.
• Figure 2: Expert evaluation results across three metrics.
• Figure 3: System prompt used for the GPT baseline in our study.