Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Prompting
Submission Type: Regular Short Paper
Submission Track: Theme Track: Large Language Models and the Future of NLP
Submission Track 2: NLP Applications
Keywords: Psychotherapy, Cognitive distortion, Cognitive behavior therapy, Large language models
TL;DR: We unveil the power of LLM to assist real professional psychotherapy by proposing the diagnosis of thought prompting for cognitive distortion detection.
Abstract: Mental illness remains one of the most critical public health issues of our time, due to the severe scarcity and accessibility limit of professionals. Psychotherapy requires high-level expertise to conduct deep, complex reasoning and analysis on the cognition modeling of the patients. In the era of Large Language Models, we believe it is the right time to develop AI assistance for computational psychotherapy. We study the task of cognitive distortion detection and propose the Diagnosis of Thought (DoT) prompting. DoT performs diagnosis on the patient's speech via three stages: subjectivity assessment to separate the facts and the thoughts; contrastive reasoning to elicit the reasoning processes supporting and contradicting the thoughts; and schema analysis to summarize the cognition schemas.
The generated diagnosis rationales through the three stages are essential for assisting the professionals. Experiments demonstrate that DoT obtains significant improvements over ChatGPT for cognitive distortion detection, while generating high-quality rationales approved by human experts.
Submission Number: 2519
Loading