Improving Reliability and Explainability of Medical Question Answering Through Atomic Fact-Checking in Retrieval-Augmented Large Language Models: Creation and Validation Study

Improving Reliability and Explainability of Medical Question Answering Through Atomic Fact-Checking in Retrieval-Augmented Large Language Models: Creation and Validation Study

Authors of this article:

Juraj Vladika¹ ;   Annika Domres² ;   Mai Nguyen² ;   Rebecca Moser² ;   Jana Nano² ;   Felix Busch³ ;   Lisa Adams³ ;   Keno K Bressem^{3, 4, 5, 6} ;   Denise Bernhardt² ;   Stephanie E Combs^{2, 7, 8} ;   Kai Borm² ;   Florian Matthes¹ ;   Jan C Peeken^{2, 7, 8}