Evaluating the accuracy of ChatGPT model versions for giving care-seeking advice
Although newer increasingly provide self-care advice, their accuracy remains insufficient for standalone use. However, making use of output variability with aggregation algorithms can improve the performance of existing models.
Authors
- Markus A. Feufel (ORCID: https://orcid.org/0000-0003-0563-8831)
- Marvin Kopka (ORCID: https://orcid.org/0000-0003-3848-1471)
- Longqi He
Institutions
- Technische Universität Berlin (DE)
Publication Details
- Journal
- Communications Medicine
- Published
- 2026-02-25
- DOI
- https://doi.org/10.1038/s43856-026-01466-0
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00