Psychological First Aid by AI: Proof‐of‐Concept and Comparative Performance of ChatGPT‐4 and Gemini in Different Disaster Scenarios
ChatGPT-4 demonstrated superior performance in providing PFA compared to Gemini. While AI chatbots show potential as supportive tools for PFA providers, concerns regarding AI hallucinations highlight the need for cautious implementation. Further research is necessary to enhance the reliability and safety of AI-assisted PFA, particularly by eliminating hallucinations, and to integrate the current advances in voice-based chatbot functionality.
Authors
- Carlos Alsua (ORCID: https://orcid.org/0000-0003-2724-6169)
- Mark Peterson (ORCID: https://orcid.org/0000-0002-3497-0203)
- Ricardo Úbeda Sales
- Jingzhi Tan (ORCID: https://orcid.org/0000-0002-7038-5626)
- Ann Zee Gan (ORCID: https://orcid.org/0009-0001-4650-5528)
- Rick Kye Gan (ORCID: https://orcid.org/0000-0002-4211-7819)
- José Antonio Cernuda Martínez (ORCID: https://orcid.org/0000-0003-2907-4081)
- Pedro Arcos González (ORCID: https://orcid.org/0000-0003-4882-5442)
Institutions
- University of Arizona (US)
- Universidad de Oviedo (ES)
- Adolfo Ibáñez University (CL)
- Royal Cornhill Hospital (GB)
Publication Details
- Journal
- Journal of Clinical Psychology
- Published
- 2025-05-09
- DOI
- https://doi.org/10.1002/jclp.23808
- Citations
- 5
- Primary Topic
- Mental Health Treatment and Access
- Type
- article
- Field-Weighted Citation Impact
- 12.19
Funders
- State University of New York
- State University of New York at New Paltz
- University at Albany