Accuracy and Completeness of Bard and Chat-GPT 4 Responses for Questions Derived from the International Consensus Statement on Endoscopic Skull-Base Surgery 2019
Chat-GPT responses are overall more accurate and complete compared with Bard, but both are very accurate and complete. Overall, rhinologists graded lower than neurosurgeons. Further research is needed to better understand the full potential of LLMs.
Authors
- Andrew Goulian (ORCID: https://orcid.org/0000-0002-4658-2451)
- Omar G. Ahmed (ORCID: https://orcid.org/0000-0002-0920-2325)
- Kayla K. Umemoto (ORCID: https://orcid.org/0000-0003-4072-7995)
- Arthur W. Wu (ORCID: https://orcid.org/0000-0001-8993-6355)
- Missael Vasquez
- Christopher R. Roxbury (ORCID: https://orcid.org/0000-0003-0686-6924)
- Pranay Soni (ORCID: https://orcid.org/0000-0003-0270-6915)
- Sean P. Polster (ORCID: https://orcid.org/0000-0002-3229-5021)
- Dennis M. Tang (ORCID: https://orcid.org/0000-0003-2315-9930)
- Yavar Abgin (ORCID: https://orcid.org/0009-0005-3363-1356)
Institutions
- Cedars-Sinai Medical Center (US)
- Cleveland Clinic (US)
- University of Chicago (US)
- Methodist Hospital (US)
- California Northstate University (US)
- Neurological Surgery (US)
- The Neurological Institute (US)
Publication Details
- Journal
- Journal of Neurological Surgery Part B Skull Base
- Published
- 2024-10-08
- DOI
- https://doi.org/10.1055/a-2436-4222
- Primary Topic
- Tracheal and airway disorders
- Type
- article
- Field-Weighted Citation Impact
- 0.00