Can Large Language Models Replace Therapists? Evaluating Performance at Simple Cognitive Behavioral Therapy Tasks
JMIR AI · 2024-07-30 · 3 · e52500
DOI: 10.2196/52500 ↗At a glance
Journal article in JMIR AI, published online on 2024-07-30. Written by Nathan Hodson and 1 co-authors. Institution: Warwick Medical School, University of Warwick, Coventry, United Kingdom. Cited 34 times so far (Crossref); 5 references. The full text is freely available in PubMed Central.
Abstract (original language)
The advent of large language models (LLMs) such as ChatGPT has potential implications for psychological therapies such as cognitive behavioral therapy (CBT). We systematically investigated whether LLMs could recognize an unhelpful thought, examine its validity, and reframe it to a more helpful one. LLMs currently have the potential to offer reasonable suggestions for the identification and reframing of unhelpful thoughts but should not be relied on to lead CBT delivery.
Subjects
Author keywords
Authors and institutions
- Warwick Medical School, University of Warwick, Coventry, United Kingdom.
ORCID profiles: Nathan Hodson, Simon Williamson
Cite
APA
Hodson, N., & Williamson, S. (2024). Can Large Language Models Replace Therapists? Evaluating Performance at Simple Cognitive Behavioral Therapy Tasks. JMIR AI, 3, e52500. https://doi.org/10.2196/52500
Vancouver
Hodson N, Williamson S. Can Large Language Models Replace Therapists? Evaluating Performance at Simple Cognitive Behavioral Therapy Tasks. JMIR AI. 2024;3:e52500. doi:10.2196/52500
BibTeX
@article{Hodson2024,
author = {Hodson, Nathan and Williamson, Simon},
title = {Can Large Language Models Replace Therapists? Evaluating Performance at Simple Cognitive Behavioral Therapy Tasks},
journal = {JMIR AI},
year = {2024},
volume = {3},
pages = {e52500},
doi = {10.2196/52500}
}
EUVIMED