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.
Keywords: CBT; ChatGPT; LLM; LLMs; NLP; artificial intelligence; chatbot; chatbots; cognitive behavioral therapy; cognitive behavioural therapy; conversational agent; conversational agents; digital therapy; language model; language models; mental health; natural language processing; performance; psychotherapy.
©Nathan Hodson, Simon Williamson. Originally published in JMIR AI (https://ai.jmir.org), 30.07.2024.