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

arXiv: https://arxiv.org/abs/2607.25681 · HTML: https://mlsanity.com/paper/2607.25681/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 70 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [A Survey of Evaluation Metrics Used for NLG Systems](https://mlsanity.com/paper/2008.12009/) (2020)
- [Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models](https://mlsanity.com/paper/2402.14848/) (2024)
- [PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support](https://mlsanity.com/paper/2106.01702/) (2021)
- [Towards Building Multilingual Language Model for Medicine](https://mlsanity.com/paper/2402.13963/) (2024)
- [Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction](https://mlsanity.com/paper/2303.04132/) (2023)
- [RankME: Reliable Human Ratings for Natural Language Generation](https://mlsanity.com/paper/1803.05928/) (2018)
- [A Framework for Human Evaluation of Large Language Models in Healthcare Derived from Literature Review](https://mlsanity.com/paper/2405.02559/) (2024)
- [CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering](https://mlsanity.com/paper/2403.16008/) (2024)
- [MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance](https://mlsanity.com/paper/2503.13509/) (2025)
- [Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs](https://mlsanity.com/paper/2503.10084/) (2025)
- [Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls](https://mlsanity.com/paper/2510.01631/) (2025)
- [Depression Detection on Social Media with Large Language Models](https://mlsanity.com/paper/2403.10750/) (2024)
- [Joint Turn and Dialogue level User Satisfaction Estimation on Multi-Domain Conversations](https://mlsanity.com/paper/2010.02495/) (2020)
- [Automated Quality Assessment of Cognitive Behavioral Therapy Sessions Through Highly Contextualized Language Representations](https://mlsanity.com/paper/2102.11573/) (2021)
- [MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media](https://mlsanity.com/paper/2410.10323/) (2024)
- [SS-GEN: A Social Story Generation Framework with Large Language Models](https://mlsanity.com/paper/2406.15695/) (2024)
- [Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product](https://mlsanity.com/paper/2502.12200/) (2025)

## Abstract (arXiv)

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.