Cognivia: A Cognitive Behavioral Therapy Copilot for Evidence-Based Mental Healthcare

2026-07-28

AI Summary

This study addresses the challenge that cognitive distortions exacerbate negative emotions and contribute to psychological disorders, while access to cognitive behavioral therapy (CBT) remains limited due to a scarcity of trained therapists. To bridge this gap, the work proposes the first lightweight AI co-therapy system that integrates authoritative CBT knowledge with expert supervision. By fine-tuning a large language model and employing multi-stage prompt engineering alongside structured response generation, the system automatically identifies cognitive distortions and produces rational, therapeutic counterstatements. The authors introduce a novel hierarchical quality evaluation framework, validated through lexical metrics, large-model-based evaluators, and manual assessments by ten behavioral science experts. Results demonstrate that the system significantly outperforms baseline methods on key tasks, offering a scalable and effective solution for CBT-informed mental health interventions.

Abstract

Cognitive distortion amplifies negative emotions and contributes to mental health disorders. Cognitive Behavioral Therapy (CBT) is an effective way to address cognitive distortions, but its large-scale application is limited by the shortage of professional therapists. Although large language models (LLMs) have recently been explored for mental health applications, existing methods still suffer from limited domain specificity, overly flattering responses, and the absence of well-defined annotations for cognitive distortions. This paper proposes Cognivia, an evidence-based artificial intelligence therapist that integrates automatic cognitive distortion identification and rational response generation. Our framework is built on authoritative CBT texts widely regarded as core paradigms and standard references. It is further augmented with mental health question-answer (Q and A) data, and employs multi-stage prompting and structured generation strategies under the supervision of behavioral science experts. Then we fine-tune a lightweight LLM on this augmented CBT dataset to obtain Cognivia. In addition, we propose the first hierarchical quality evaluation framework for assessing LLM-generated rational responses, developed through collaboration between AI researchers and behavioral science experts. Cognivia is evaluated using lexical metrics, LLM-based Judges with two complementary criteria, and human evaluation by 10 behavioral science experts. It consistently outperforms the baseline methods in cognitive distortion recognition and rational response generation, demonstrating its effectiveness. Our code is available at https://github.com/SNOWTEAM2023/Cognivia.

Problem

• Cognitive Distortion
• Cognitive Behavioral Therapy
• Mental Health
• Large Language Models
• Evidence-Based Therapy

Innovation

• Cognitive Behavioral Therapy
• Cognitive Distortion Identification
• Rational Response Generation
• Evidence-Based AI
• Hierarchical Evaluation Framework