Have you ever wondered how artificial intelligence can be used to analyze historical sources? Much like in the natural sciences, the rapid progress of digitization is also leading to fundamental changes in work processes within the humanities. This development goes beyond the mere storage and presentation of scholarly data and is increasingly influencing the research process itself by transforming the methods of knowledge generation. In particular, the introduction of large language models (such as ChatGPT) has revolutionized historical research processes. Historical sources no longer need to be laboriously and time-consumingly analyzed by hand; instead, the information can now be extracted automatically.
Through our participation in the Long Night of Science, we would like to present the potential applications of artificial intelligence in the research conducted by our interdisciplinary working group, consisting of computer scientists and historians. Our group is called MEPHIsto (“Digital Models, Explanations, and Processes in the Historical Sciences”). We are examining the administrative records of the late medieval church, which are published in the *Repertorium Germanicum*. This source offers a rich and multifaceted picture of the late medieval Church, including its religious and canon-legal foundations, organizational and fiscal mechanisms, personnel and spatial networks, as well as political ambitions and everyday realities.
As an example, we will demonstrate how we used Large Language Models to analyze financial transactions between Germany and the Roman Curia in the 15th century under Pope Sixtus IV. In this way, we were able to algorithmically identify a clearly structured network of key financial actors of that era.
During the hands-on session, you’ll have the opportunity to evaluate historical sources yourself and find out whether your own ancestors were involved in the processes of the late medieval Church. Use state-of-the-art large language models to discover fascinating connections. We’re also offering a “grammar building blocks” mini-game where you can parse a short, semi-structured text in German or Latin.