Identifying Biomedical Entities for Datasets in Scientific Articles: 4-Step Cache-Augmented Generation Approach Using GPT-4o and PubTator 3.0

Claudia Giuliani   ¹ , PhD ;   Gita Benadi   ¹ , PhD ;   Felix Engel   ¹ , PhD ;   Jonas Werner   ¹ , MSc ;   Manuel Watter   ¹ , MSc ;   Guido Schwarzer   ¹ , PhD ;   Olaf Groß   ^{2, 3} , PhD ;   Robert Zeiser   ^{3, 4} , MD ;   Harald Binder   ^{1, 3} , PhD ;   Klaus Kaier   ^{1, 3} , PhD

¹ Institute of Medical Biometry and Statistics, Medical Faculty and Medical Center, University of Freiburg, Freiburg, Germany

² Institute of Neuropathology, Medical Faculty and Medical Center, University of Freiburg, Freiburg, Germany

³ Center for Integrative Biological Signaling Studies, University of Freiburg, Freiburg, Germany

⁴ Department of Medicine I, Medical Faculty and Medical Center, University of Freiburg, Freiburg, Germany