Retrieval-Augmented Generation for Large Language Models in Radiology: Another Leap Forward in Board Examination Performance
Radiology · 01.10.2024 · 313 (1)
DOI: 10.1148/radiol.241489 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiology, erschienen am 01.10.2024. Verfasst von Rajesh Bhayana und 4 weiteren Autor:innen. Beteiligte Einrichtung: From the University Medical Imaging Toronto, Joint Department of Medical Imaging, Toronto General Hospital, Department of Medical Imaging, University…. Hauptthemen laut MEDLINE: Radiology. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 2 Literaturangaben.
Abstract (Originalsprache)
Perplexity (Perplexity AI), which uses web-based retrieval-augmented generation (RAG) and prioritizes authoritative sources, with GPT-4 Turbo (OpenAI) outperformed default GPT-4 Turbo on a radiology board–style examination, illustrating the utility of RAG optimization to generate radiology answers.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- From the University Medical Imaging Toronto, Joint Department of Medical Imaging, Toronto General Hospital, Department of Medical Imaging, University of Toronto, 200 Elizabeth St, Peter Munk Bldg, 1st Fl, Toronto, ON, C…
ORCID-Profile: Rajesh Bhayana, Aly Fawzy, Yangqing Deng, Robert R Bleakney, Satheesh Krishna
Zitieren
APA
Bhayana, R., Fawzy, A., Deng, Y., Bleakney, R. R., & Krishna, S. (2024). Retrieval-Augmented Generation for Large Language Models in Radiology: Another Leap Forward in Board Examination Performance. Radiology, 313(1). https://doi.org/10.1148/radiol.241489
Vancouver
Bhayana R, Fawzy A, Deng Y, Bleakney RR, Krishna S. Retrieval-Augmented Generation for Large Language Models in Radiology: Another Leap Forward in Board Examination Performance. Radiology. 2024;313(1). doi:10.1148/radiol.241489
BibTeX
@article{Bhayana2024,
author = {Bhayana, Rajesh and Fawzy, Aly and Deng, Yangqing and Bleakney, Robert R and Krishna, Satheesh},
title = {Retrieval-Augmented Generation for Large Language Models in Radiology: Another Leap Forward in Board Examination Performance},
journal = {Radiology},
year = {2024},
volume = {313},
number = {1},
doi = {10.1148/radiol.241489}
}
EUVIMED