In-depth analysis of ChatGPT’s performance based on specific signaling words and phrases in the question stem of 2377 USMLE step 1 style questions

Leonard Knoedler, Samuel Knoedler, Cosima C. Hoch, Lukas Prantl, Konstantin Frank, Laura Soiderer, Sebastian Cotofana, Amir H. Dorafshar, Thilo Schenck, Felix Vollbach, Giuseppe Sofo, Michael Alfertshofer

Open source

DOI
10.1038/s41598-024-63997-7
Published
2024-06-12
Container
Scientific Reports
Publisher
Springer Science and Business Media LLC
Open access
unknown

Credibility signals

uncertain Score 64/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1038/s41598-024-63997-7,
  title = {In-depth analysis of ChatGPT’s performance based on specific signaling words and phrases in the question stem of 2377 USMLE step 1 style questions},
  author = {Leonard Knoedler and Samuel Knoedler and Cosima C. Hoch and Lukas Prantl and Konstantin Frank and Laura Soiderer and Sebastian Cotofana and Amir H. Dorafshar and Thilo Schenck and Felix Vollbach and Giuseppe Sofo and Michael Alfertshofer},
  year = {2024},
  journal = {Scientific Reports},
  doi = {10.1038/s41598-024-63997-7},
  url = {https://doi.org/10.1038/s41598-024-63997-7}
}

RIS

TY  - JOUR
TI  - In-depth analysis of ChatGPT’s performance based on specific signaling words and phrases in the question stem of 2377 USMLE step 1 style questions
AU  - Leonard Knoedler
AU  - Samuel Knoedler
AU  - Cosima C. Hoch
AU  - Lukas Prantl
AU  - Konstantin Frank
AU  - Laura Soiderer
AU  - Sebastian Cotofana
AU  - Amir H. Dorafshar
AU  - Thilo Schenck
AU  - Felix Vollbach
AU  - Giuseppe Sofo
AU  - Michael Alfertshofer
PY  - 2024
JO  - Scientific Reports
DO  - 10.1038/s41598-024-63997-7
UR  - https://doi.org/10.1038/s41598-024-63997-7
ER  - 

APA

Knoedler, L., Knoedler, S., Hoch, C. C., Prantl, L., Frank, K., Soiderer, L., Cotofana, S., Dorafshar, A. H., Schenck, T., Vollbach, F., Sofo, G., & Alfertshofer, M. (2024). In-depth analysis of ChatGPT’s performance based on specific signaling words and phrases in the question stem of 2377 USMLE step 1 style questions. Scientific Reports. https://doi.org/10.1038/s41598-024-63997-7

Source records