Fidelity of Medical Reasoning in Large Language Models
This cross-sectional study evaluates whether the performance of large language models on medical benchmarks reflects logical reasoning or pattern recognition.
Authors
- Nigam H. Shah (ORCID: https://orcid.org/0000-0001-9385-7158)
- Suhana Bedi (ORCID: https://orcid.org/0000-0002-4502-4191)
- Oluwasanmi Koyejo (ORCID: https://orcid.org/0000-0002-4023-419X)
- Philip Chung (ORCID: https://orcid.org/0000-0002-1194-7510)
- Yixing Jiang (ORCID: https://orcid.org/0009-0003-0008-091X)
Institutions
- Stanford Medicine (US)
- Stanford University (US)
Publication Details
- Journal
- JAMA Network Open
- Published
- 2025-08-08
- DOI
- https://doi.org/10.1001/jamanetworkopen.2025.26021
- Citations
- 18
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 11.78
Funders
- National Science Foundation
- John D. and Catherine T. MacArthur Foundation
- Gordon and Betty Moore Foundation
- Institute of Education Sciences