Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhou, Jinfeng, Chen, Yuxuan, Yin, Jianing, Huang, Yongkang, Shi, Yihan, Zhang, Xikun, Peng, Libiao, Zhang, Rongsheng, Lv, Tangjie, Hu, Zhipeng, Wang, Hongning, Huang, Minlie
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910917888835584
author Zhou, Jinfeng
Chen, Yuxuan
Yin, Jianing
Huang, Yongkang
Shi, Yihan
Zhang, Xikun
Peng, Libiao
Zhang, Rongsheng
Lv, Tangjie
Hu, Zhipeng
Wang, Hongning
Huang, Minlie
author_facet Zhou, Jinfeng
Chen, Yuxuan
Yin, Jianing
Huang, Yongkang
Shi, Yihan
Zhang, Xikun
Peng, Libiao
Zhang, Rongsheng
Lv, Tangjie
Hu, Zhipeng
Wang, Hongning
Huang, Minlie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17238
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues
Zhou, Jinfeng
Chen, Yuxuan
Yin, Jianing
Huang, Yongkang
Shi, Yihan
Zhang, Xikun
Peng, Libiao
Zhang, Rongsheng
Lv, Tangjie
Hu, Zhipeng
Wang, Hongning
Huang, Minlie
Computation and Language
Human-Computer Interaction
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.
title Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2504.17238