mlsanityData to 14 Oct 2026

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

arXiv 2504.17238 ↗First posted 24 Apr 2025cs.CL cs.HCcited by 11

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

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.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 27 of its 68 references that are in the map. First posted on arXiv 24 Apr 2025.

Builds on

27 of 68 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Does "Reasoning" with Large Language Models Improve Recognizing, Generating, and Reframing Unhelpful Thoughts?31 Mar
  2. 2025Multimodal Cognitive Reframing Therapy via Multi-hop Psychotherapeutic Reasoning8 Feb
  3. 2023SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations1 Nov
  4. 2023Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts6 Jul

Other references · 23

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2021Towards Emotional Support Dialog Systemscited by 299
  5. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
  6. 2022SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualizationcited by 168
  7. 2022ProsocialDialog: A Prosocial Backbone for Conversational Agentscited by 109
  8. 2024CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counselingcited by 89
  9. 2022AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversationcited by 79
  10. 2023Cognitive Reframing of Negative Thoughts through Human-Language Model Interactioncited by 77
  11. 2024OpenELM: An Efficient Language Model Family with Open Training and Inference Frameworkcited by 75
  12. 2024Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principlescited by 73
11 more
  1. 2023Building Emotional Support Chatbots in the Era of LLMscited by 62
  2. 2024Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theorycited by 60
  3. 2024HealMe: Harnessing Cognitive Reframing in Large Language Models for Psychotherapycited by 47
  4. 2024ESCoT: Towards Interpretable Emotional Support Dialogue Systemscited by 46
  5. 2024CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answeringcited by 45
  6. 2024Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactionscited by 43
  7. 2022Inducing Positive Perspectives with Text Reframingcited by 31
  8. 2022CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generationcited by 18
  9. 2025MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistancecited by 13
  10. 2024Socratic Reasoning Improves Positive Text Rewritingcited by 9
  11. 2025Exploratory Study into Relations between Cognitive Distortions and Emotional Appraisalscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 9.

11 papers.

  1. 2025Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Modelscited by 21
  2. 2025Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivitycited by 5
  3. 2026PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethicscited by 4
  4. 2026PatientHub: A Unified Framework for Patient Simulationcited by 4
  5. 2026Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counselingcited by 4
  6. 2026PsychePass: Calibrating LLM Therapeutic Competence via Trajectory-Anchored Tournamentscited by 2
  7. 2026Responsible Evaluation of AI for Mental Healthcited by 2
  8. 2026EFT-CoT: A Multi-Agent Chain-of-Thought Framework for Emotion-Focused Therapycited by 1
  9. 2026EmoTrace: An Emotion Trajectory-Centered Framework for Psychological Support Dialogue Generationcited by 0
  10. 2026AnchorSIPS: A Synthetic Dataset and Evaluation Resource for Evidence-Supported Psychosis-Risk Symptom Measurementcited by 0
  11. 2026From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Healthcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Why It Hurts: Identifying the Drivers of Negative Thoughts in Emotional Support Conversations
  2. 2026StageWell: A Process-Aligned Chinese Corpus for Positive-Psychology Support Dialogue
  3. 2026Reasoning Over Recall: Evaluating the Efficacy of Generalist Architectures vs. Specialized Fine-Tunes in RAG-Based Mental Health Dialogue Systems
  4. 2025Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling
  5. 2025Psy-Insight: Explainable Multi-turn Bilingual Dataset for Mental Health Counseling
  6. 2025MindEval: Benchmarking Language Models on Multi-turn Mental Health Support
  7. 2025CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation
  8. 2026OMIND: Framework for Knowledge Grounded Finetuning and Multi-Turn Dialogue Benchmark for Mental Health LLMs