Creating a biomedical knowledge base by addressing GPT inaccurate responses and benchmarking context
Shelby S. Darnell, Rupert W. Overall, Andrea Guarracino, Vicenza Colonna, Flavia Villani, Erik P. Garrison, Arun Isaac, Priscilla Muli, Muriithi Frederick Muriuki, Alexander Kabui, Munyoki Kilyungi, Felix Lisso, Adrian Kibet, Brian Muhia, Harm Nijveen, , Pjotr Prins
GNQA, a retrieval-augmented GPT question-answering system over 3000 GeneNetwork, aging and diabetes papers, cites source paragraphs; RAGAS rated answer relevance above human thumbs-up ratings (89% vs 76%).
Open Research Africa · Sep 2, 2025Peer-reviewedScientific Communication & Education✦ In-depth digest