RadioRAG: Online Retrieval–Augmented Generation for Radiology Question Answering
Soroosh Tayebi Arasteh, Mahshad Lotfinia, Keno K. Bressem, Robert Siepmann, Lisa Adams, Dyke Ferber, Christiane Kühl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn
Abstract
RadioRAG uses online retrieval–augmented generation to potentially improve the accuracy and factuality of large language model–generated responses to case-based radiology questions by incorporating real-time data from Radiopaedia.
Topics & Concepts
Computer scienceMedical physicsNatural language processingMedicineTopic ModelingComputational and Text Analysis MethodsNatural Language Processing Techniques