PSY-STEP: Structuring Therapeutic Targets and Action Sequences for Proactive Counseling Dialogue Systems
This work addresses the challenge of building effective proactive counseling dialogue systems for mental health applications, representing an incremental improvement with a novel dataset and method.
The paper tackles the problem of counseling agents struggling to identify and address automatic negative thoughts in Cognitive Behavioral Therapy (CBT) dialogues by introducing STEP, a dataset modeling CBT with automatic thoughts and action sequences, and training STEPPER, a proactive counseling agent refined through preference learning. The result shows that STEPPER delivers more clinically grounded, coherent, and personalized counseling with higher counselor competence compared to baselines.
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.