Assessing ChatGPT-4’s performance on the US prosthodontic exam: impact of fine-tuning and contextual prompting vs. base knowledge, a cross-sectional study
Fine-tuning ChatGPT-4 with specific resources significantly enhances its accuracy in answering specialized prosthodontic exam questions. While the base model provides a solid baseline, fine-tuning is essential for improving AI performance in specialized fields. However, certain topics may require more targeted training to achieve higher accuracy.
Authors
- Amir Fahimipour (ORCID: https://orcid.org/0000-0002-0218-2181)
- Farshad Khosraviani (ORCID: https://orcid.org/0000-0001-6304-4770)
- Delband Hefzi (ORCID: https://orcid.org/0009-0008-2085-3584)
- Zohaib Khurshid (ORCID: https://orcid.org/0000-0001-7998-7335)
- Mahmood Dashti (ORCID: https://orcid.org/0000-0003-2013-0374)
- Shohreh Ghasemi (ORCID: https://orcid.org/0000-0002-2298-4616)
- Syed Rashid Habib
- Niusha Zare (ORCID: https://orcid.org/0000-0002-5484-8176)
- Tara Azimi
Institutions
- University of Southern California (US)
- The University of Sydney (AU)
- Chulalongkorn University (TH)
- Queen Mary University of London (GB)
- University of Tehran (IR)
- UCLA Health (US)
- King Saud University (SA)
- Westmead Hospital (AU)
- Shahid Beheshti University of Medical Sciences (IR)
Publication Details
- Journal
- BMC Medical Education
- Published
- 2025-05-23
- DOI
- https://doi.org/10.1186/s12909-025-07371-9
- Citations
- 8
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 5.23
Funders
- King Saud University
- King Faisal University