Large language models (LLMs) in the evaluation of emergency radiology reports: performance of ChatGPT-4, Perplexity, and Bard

A. Infante; Simona Gaudino; Federico Orsini; Annemilia Del Ciello; C. Gullì; Biagio Merlino; Luigi Natale; Roberto Iezzi; Evis Sala

doi:10.1016/j.crad.2023.11.011

Large language models (LLMs) in the evaluation of emergency radiology reports: performance of ChatGPT-4, Perplexity, and Bard

A. Infante, Simona Gaudino, Federico Orsini, Annemilia Del Ciello, C. Gullì, Biagio Merlino, Luigi Natale, Roberto Iezzi, Evis Sala

Research output: Contribution to journal › Article

Original language	English
Pages (from-to)	102-106
Number of pages	5
Journal	Clinical Radiology
Volume	79
DOIs	https://doi.org/10.1016/j.crad.2023.11.011
Publication status	Published - 2024

Keywords

chatGPT

Access to Document

10.1016/j.crad.2023.11.011

Cite this

@article{600b7e0e0fde4cf7bcb3a5a9c463df59,

title = "Large language models (LLMs) in the evaluation of emergency radiology reports: performance of ChatGPT-4, Perplexity, and Bard",

keywords = "chatGPT, chatGPT",

author = "A. Infante and Simona Gaudino and Federico Orsini and {Del Ciello}, Annemilia and C. Gull{\`i} and Biagio Merlino and Luigi Natale and Roberto Iezzi and Evis Sala",

year = "2024",

doi = "10.1016/j.crad.2023.11.011",

language = "English",

volume = "79",

pages = "102--106",

journal = "Clinical Radiology",

issn = "0009-9260",

publisher = "W.B. Saunders Ltd",

}

TY - JOUR

T1 - Large language models (LLMs) in the evaluation of emergency radiology reports: performance of ChatGPT-4, Perplexity, and Bard

AU - Infante, A.

AU - Gaudino, Simona

AU - Orsini, Federico

AU - Del Ciello, Annemilia

AU - Gullì, C.

AU - Merlino, Biagio

AU - Natale, Luigi

AU - Iezzi, Roberto

AU - Sala, Evis

PY - 2024

Y1 - 2024

KW - chatGPT

UR - http://hdl.handle.net/10807/271349

U2 - 10.1016/j.crad.2023.11.011

DO - 10.1016/j.crad.2023.11.011

M3 - Article

SN - 0009-9260

VL - 79

SP - 102

EP - 106

JO - Clinical Radiology

JF - Clinical Radiology

ER -

Large language models (LLMs) in the evaluation of emergency radiology reports: performance of ChatGPT-4, Perplexity, and Bard

Keywords

Access to Document

Other files and links

Cite this