Performance of the Large Language Models on the Chinese National Nurse Licensure Examination: Cross-Sectional Evaluation Study
While some LLMs show promising accuracy on the CNNLE, fundamental reliability limitations (poor confidence calibration and inconsistent repeatability) hinder safe application in nursing education and practice. Future LLM development must prioritize trustworthiness and calibrated reliability over surface accuracy.
Authors
- Renxiu Wang (ORCID: https://orcid.org/0009-0006-0932-5786)
- Longhui Xu (ORCID: https://orcid.org/0009-0008-2790-8701)
- Ronghui Wang (ORCID: https://orcid.org/0009-0007-2025-6459)
- Xinru Liu (ORCID: https://orcid.org/0009-0008-7676-7925)
- Xu Cuiping (ORCID: https://orcid.org/0000-0002-8868-4878)
- Na Li (ORCID: https://orcid.org/0009-0004-7582-3113)
- Xiao Cong (ORCID: https://orcid.org/0009-0009-5066-0676)
Institutions
- Shandong University of Traditional Chinese Medicine (CN)
- Shandong Provincial QianFoShan Hospital (CN)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-11-03
- DOI
- https://doi.org/10.2196/78279
- Primary Topic
- Medical Education and Admissions
- Type
- article
- Field-Weighted Citation Impact
- 0.00