Ability of AI detection tools and humans to accurately identify different forms of AI-generated written content
While existing AI detection tools can meaningfully distinguish plausible AI use conditions, reliability across these tools is variable. Human scoring accuracy is uniformly low. Use of AI detection tools by scholars and journal editors may assist in determining potentially unethical use but they should not be relied upon alone at this time.
Authors
- Viviane Mallette
- David Krieser (ORCID: https://orcid.org/0000-0002-7173-6993)
- Yiqun Lin (ORCID: https://orcid.org/0000-0002-4726-5992)
- Samantha Wirkowski
- Gabriel Reedy (ORCID: https://orcid.org/0000-0002-1839-1949)
- Christine L.M. Joseph (ORCID: https://orcid.org/0000-0003-0069-4391)
- Adam Cheng (ORCID: https://orcid.org/0000-0002-1039-7502)
- Aaron W. Calhoun (ORCID: https://orcid.org/0000-0003-0937-815X)
- Vikhashni Nagesh
Institutions
- University of Louisville (US)
- The University of Melbourne (AU)
- University of Calgary (CA)
- King's College London (GB)
- Centre Hospitalier Universitaire de Sherbrooke (CA)
- Alberta Children's Hospital (CA)
- Kosair Children's Hospital (US)
- King's College School (GB)
- Norton Hospital (US)
- University of Louisville Hospital (US)
Publication Details
- Journal
- Advances in Simulation
- Published
- 2025-11-22
- DOI
- https://doi.org/10.1186/s41077-025-00396-6
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00