ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance
Javier Rodriguez-Juan, Hiba Arnaout, Jose Garcia-Rodriguez, David Tomás, Iryna Gurevych
cs.CL, cs.LG
Submitted: 2026-08-05
Comments: 39 pages, 23 figures, 12 tables
License: http://creativecommons.org/licenses/by/4.0/
The gist: Synthetic generation of Cognitive Behavioral Therapy (CBT) sessions is challenged by two competing demands: adhering to strict therapeutic structure while modeling the resistant, unpredictable
Terminology
Abstract
Synthetic generation of Cognitive Behavioral Therapy (CBT) sessions is challenged by two competing demands: adhering to strict therapeutic structure while modeling the resistant, unpredictable behavior of real patients. Existing script-based methods fail to capture dynamic therapeutic interactions, while multi-agent approaches struggle to adhere to CBT's sequential structure; both suffer from sycophancy, producing overly compliant patients that misrepresent real clinical settings. In this work we introduce ODRA, a novel framework for synthesizing therapy dialogues through a Chain-of-Thought (CoT) strategy grounded in foundational CBT guidelines (Beck, 2020). ODRA further incorporates a resistance orchestrator to solve patient sycophancy, which employs steering techniques to elicit behaviors aligned with their resistance level. Automated and expert evaluations show that ODRA significantly outperforms existing methods across therapeutic skills, CBT alignment, and patient behavioral fidelity, with licensed psychologists preferring ODRA sessions across 12 of 13 clinical metrics. Furthermore, models fine-tuned on our dataset demonstrate superior therapeutic performance against both cooperative and resistant patients, validating that explicit resistance modeling in synthetic training data directly translates to downstream clinical robustness.
Sources
- Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness
- Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs
- MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions
- CALM-IT: Enhancing Synthetic Motivational Interviewing Dialogue Quality with Conversational Dynamics
- AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
- A Decade-Scale Benchmark Evaluating LLMs' Clinical Practice Guidelines Detection and Adherence in Multi-turn Conversations
- Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering