Are clinical improvements in large language models a reality? Longitudinal comparisons of ChatGPT models and DeepSeek-R1 for psychiatric assessments and interventions.

Journal: The International journal of social psychiatry
Published Date: Jul 31, 2025

Abstract

BACKGROUND: Potential clinical applications for emerging large-language models (LLMs; e.g. ChatGPT) are well-documented, and newer systems (e.g. DeepSeek) have attracted increasing attention. Yet, important questions endure about their reliability and cultural responsiveness in psychiatric settings.

Authors

  • Alexander Smith
    Department of Forensic Psychiatry, University of Bern, Switzerland.
  • Michael Liebrenz
    Department of Forensic Psychiatry, University of Bern, Switzerland.
  • Dinesh Bhugra
    Kings College London, Institute of Psychiatry, London, UK.
  • Juan Grana
    Department of Forensic Psychiatry, University of Bern, Switzerland.
  • Roman Schleifer
    Department of Forensic Psychiatry, University of Bern, Switzerland.
  • Ana Buadze
    Psychiatric University Hospital, University of Zurich, Switzerland.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals