Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Jihyun Lee, Yejin Min, Yejin Jeon, SungJun Yang, Hyounghun Kim, Gary Geunbae Lee

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.

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

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.

Paper Structure

This paper contains 82 sections, 6 figures, 18 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Modeling Client States in Counseling.
  4. Psy-Step: Structured Counseling Dataset for CBT
  5. Client Profile Construction
  6. Planning and Dialogue Generation
  7. Plan and Action Sequence Construction.
  8. Dialogue Generation.
  9. Dialogue Filtering and Quality Control
  10. Expert Review of Dataset
  11. Comparison Psy-Step with Existing Counseling Datasets
  12. Stepper: Structured CBT Counseling Model
  13. Preference Tuning.
  14. Experimental Settings
  15. Counselor Agent Variants
  16. ...and 67 more sections

Figures (6)

  • Figure 1: Example of a structured CBT interaction for eliciting automatic thoughts and cognitive reframing.
  • Figure 2: Overview of the Psy-Step dataset construction and structured CBT counseling flow. The figure illustrates how client profiles are modeled, how surface-level problems and automatic thoughts are elicited during the diagnostic stage, and how structured action sequences guide therapeutic interventions through stepwise CBT reasoning.
  • Figure 3: Illustration of the simulation-based process for collecting preference data for utterance selection.
  • Figure 4: Preference comparisons of Stepper, conducted with Gemini-based clients and evaluators.
  • Figure 5: Preference comparison of Stepper conducted with human experts (see Appendix \ref{['app:human_AB_test_model']} for details).
  • ...and 1 more figures