Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues
This addresses the shortage of clinicians and stigma in mental health therapy by providing an interactive AI system for cognitive restructuring, though it is incremental as it builds on existing LLM and dialogue methods.
The authors tackled the problem of automating Cognitive Restructuring (CR) for mental health by developing CRDial, a framework for multi-turn supportive dialogues, and Crispers, conversational LLMs trained on a distilled dataset, which showed superiority in human evaluations.
Cognitive Restructuring (CR) is a psychotherapeutic process aimed at identifying and restructuring an individual's negative thoughts, arising from mental health challenges, into more helpful and positive ones via multi-turn dialogues. Clinician shortage and stigma urge the development of human-LLM interactive psychotherapy for CR. Yet, existing efforts implement CR via simple text rewriting, fixed-pattern dialogues, or a one-shot CR workflow, failing to align with the psychotherapeutic process for effective CR. To address this gap, we propose CRDial, a novel framework for CR, which creates multi-turn dialogues with specifically designed identification and restructuring stages of negative thoughts, integrates sentence-level supportive conversation strategies, and adopts a multi-channel loop mechanism to enable iterative CR. With CRDial, we distill Crisp, a large-scale and high-quality bilingual dialogue dataset, from LLM. We then train Crispers, Crisp-based conversational LLMs for CR, at 7B and 14B scales. Extensive human studies show the superiority of Crispers in pointwise, pairwise, and intervention evaluations.