Are Large Language Models Possible to Conduct Cognitive Behavioral Therapy?

TL;DR

This study investigates whether large language models can effectively conduct cognitive behavioral therapy by evaluating their emotional, conversational, and inquiry abilities using a comprehensive automatic framework.

Contribution

The paper introduces a novel evaluation framework for assessing LLMs' CBT capabilities and demonstrates their potential with enhanced performance after integrating a CBT knowledge base.

Findings

LLMs show significant potential in psychological counseling.

Integration of a CBT knowledge base improves LLMs' counseling abilities.

Evaluation metrics effectively measure emotion, dialogue structure, and proactive inquiry in LLM-generated CBT dialogues.

Abstract

In contemporary society, the issue of psychological health has become increasingly prominent, characterized by the diversification, complexity, and universality of mental disorders. Cognitive Behavioral Therapy (CBT), currently the most influential and clinically effective psychological treatment method with no side effects, has limited coverage and poor quality in most countries. In recent years, researches on the recognition and intervention of emotional disorders using large language models (LLMs) have been validated, providing new possibilities for psychological assistance therapy. However, are LLMs truly possible to conduct cognitive behavioral therapy? Many concerns have been raised by mental health experts regarding the use of LLMs for therapy. Seeking to answer this question, we collected real CBT corpus from online video websites, designed and conducted a targeted automatic evaluation framework involving the evaluation of emotion tendency of generated text, structured dialogue pattern and proactive inquiry ability. For emotion tendency, we calculate the emotion tendency score of the CBT dialogue text generated by each model. For structured dialogue pattern, we use a diverse range of automatic evaluation metrics to compare speaking style, the ability to maintain consistency of topic and the use of technology in CBT between different models . As for inquiring to guide the patient, we utilize PQA (Proactive Questioning Ability) metric. We also evaluated the CBT ability of the LLM after integrating a CBT knowledge base to explore the help of introducing additional knowledge to enhance the model's CBT counseling ability. Four LLM variants with excellent performance on natural language processing are evaluated, and the experimental result shows the great potential of LLMs in psychological counseling realm, especially after combining with other technological means.