PSY-STEP: Structuring Therapeutic Targets and Action Sequences for Proactive Counseling Dialogue Systems

TL;DR

This paper introduces STEP, a new dataset and counseling agent for CBT that proactively identifies automatic thoughts and executes interventions, improving clinical relevance and personalization.

Contribution

The paper presents a novel dataset and a counseling agent trained on it, with preference learning for better decision-making and empathy in dialogue-based CBT counseling.

Findings

STEPPER outperforms baseline models in clinical relevance and coherence.

The system achieves higher counselor competence without emotional disruption.

Preference learning enhances decision accuracy and empathic responsiveness.

Abstract

Cognitive Behavioral Therapy (CBT) aims to identify and restructure automatic negative thoughts pertaining to involuntary interpretations of events, yet existing counseling agents struggle to identify and address them in dialogue settings. To bridge this gap, we introduce STEP, a dataset that models CBT counseling by explicitly reflecting automatic thoughts alongside dynamic, action-level counseling sequences. Using this dataset, we train STEPPER, a counseling agent that proactively elicits automatic thoughts and executes cognitively grounded interventions. To further enhance both decision accuracy and empathic responsiveness, we refine STEPPER through preference learning based on simulated, synthesized counseling sessions. Extensive CBT-aligned evaluations show that STEPPER delivers more clinically grounded, coherent, and personalized counseling compared to other strong baseline models, and achieves higher counselor competence without inducing emotional disruption.