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

Juraj Vladika   ^{1 *} , PhD ;   Annika Domres   ^{2 *} ;   Mai Nguyen   ² , Dr med ;   Rebecca Moser   ² , Dr med ;   Jana Nano   ² , Dsc, PhD ;   Felix Busch   ³ , Dr med ;   Lisa Adams   ³ , Prof Dr med ;   Keno K Bressem   ^{3, 4, 5, 6} , Prof Dr med ;   Denise Bernhardt   ² , Dr med ;   Stephanie E Combs   ^{2, 7, 8} , Prof Dr med ;   Kai Borm   ² , Prof Dr med ;   Florian Matthes   ¹ , Prof Dr ;   Jan C Peeken   ^{2, 7, 8} , Prof Dr med, PhD

¹ Department of Computer Science, TUM School of Computation Information and Technology, Technical University of Munich, Garching, Bavaria, Germany

² Department of Radiation Oncology, TUM University Hospital Rechts der Isar, TUM School of Medicine and Health, Technical University of Munich, Munich, Bavaria, Germany

³ Department of Diagnostic and Interventional Radiology, TUM University Hospital Rechts der Isar, TUM School of Medicine and Health, Technical University of Munich, Munich, Germany

⁴ National Center for Tumor Diseases West, Essen, Germany

⁵ Institute of Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany

⁶ Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Essen, Germany

⁷ Institute of Radiation Medicine (IRM), Helmholtz Zentrum München (HMGU), Munich, Bavaria, Germany

⁸ German Consortium for Translational Cancer Research (DKTK), Partner Site Munich, Munich, Bavaria, Germany

*these authors contributed equally