Search papers, labs, and topics across Lattice.
This paper introduces ODRA, a novel framework for synthesizing Cognitive Behavioral Therapy (CBT) sessions that effectively balances adherence to therapeutic structure with the dynamic behaviors of resistant patients. By employing a Chain-of-Thought strategy and a resistance orchestrator, ODRA mitigates the issue of sycophancy found in previous methods, resulting in more realistic and clinically relevant therapy dialogues. Evaluations reveal that ODRA significantly outperforms existing approaches in therapeutic skills and patient fidelity, with licensed psychologists favoring its sessions across nearly all clinical metrics.
ODRA's innovative approach to modeling patient resistance leads to synthetic therapy sessions that are not only more realistic but also preferred by licensed psychologists.
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.
