Work

Llama 3 Challenges Proprietary State-of-the-Art Large Language Models in Radiology Board–style Examination Questions

Year: 2024

Type: article

Abstract: Meta’s Llama 3, an open-source large language model, performed on par with larger proprietary models, such as OpenAI’s GPT-4 and Anthropic’s Claude 3 Opus, on a subset of radiology board-style examination questions, highlighting the potential of open-source artificial intelligence in radiology.

Source: Radiology

DOI: 10.1148/radiol.241191

Authors: Lisa C. Adams, Daniel Truhn, Felix Busch, Felix Dorfner, Jawed Nawabi, Marcus R. Makowski, Keno K. Bressem

Institutions: Humboldt-Universität zu Berlin, Universitätsklinikum Aachen, Deutsches Herzzentrum München, Technical University of Munich, Freie Universität Berlin, Charité - Universitätsmedizin Berlin, RWTH Aachen University

Language: English

Topic: Artificial Intelligence in Healthcare and Education

Subfield: Health Informatics

Field: Medicine

Domain: Health Sciences

Open Access status: bronze

Funder: European Commission

Awards: COMputational Models FOR patienT stratification in urologic cancers – Creating robust and trustworthy multimodal AI for health care, A Collective Intelligence Platform to Support Cancer Champions, IMAGING AND ADVANCED GUIDANCE FOR WORKFLOW OPTIMIZATION IN INTERVENTIONAL ONCOLOGY

OpenAlex ID: W4401548565

FWCI: 2.85

Cites: 5

Cited by: 35

Related to: 10