Large language models (LLMs) as psychotherapists: an analysis based on psychodynamic psychotherapy theory

Abstract

The article analyses the capabilities and limitations of large language models’ (LLMs) powering chat interfaces, such as ChatGPT, in the context of their potential use as “psychotherapists”. The authors relate this issue to the principles of psychodynamic psychotherapy, in which interpersonal relationships, unconscious processes, transference, and countertransference are of key importance. Based on a review of the literature and technical analysis, it is indicated that contemporary LLMs do not meet the basic conditions for conducting therapy in this field. They lack awareness, emotionality, and the ability to mentalize, whereas their “empathy” is purely linguistic and simulated. Human interactions with the model can create the illusion of a therapeutic relationship, promote anthropomorphizing and excessive trust in the algorithm. The article highlights the ethical, legal, and purely psychological risks associated with assigning chatbots the role of therapists. The analysis encompasses problems of hallucinations, data bias, and lack of ethical oversight. At the same time, the authors point to the potential benefits of using LLMs as support tools – in psychological education, preliminary diagnosis, stress reduction, or as a support for therapists in the process of analysis. They emphasize the need for an interdisciplinary approach combining psychology, law, and ethics, as well as the need to develop standards for safety and oversight of the use of LLMs in the field of mental health. The article concludes with a call for caution in the face of the growing integration of technology into therapeutic practice.