Report on a hybrid conference in Marburg, 12–13 December 2024
In the years to come, curatorial and archival processes in memory and heritage institutions (including key aspects of cataloguing such as description, classification and categorization) will be increasingly supported by automated systems and artificial intelligence. These practices attribute value to sources and link archival materials and collection objects to societal narratives. Collections and archives thus form an essential basis for memory-related discourses and shape our view of the past. New technologies have now reached the stage where they are potentially suitable for the requirements of cultural heritage institutions. There is substantial promise in the partially automated indexing and cataloguing of historical sources, particularly of digital images, the hermeneutics and meaning of images which in the past have only been accessible to the human eye and not the machine.
Images can now be automatically described semantically, making them easier to find. AI methods – and most recently multimodal AI processing – are opening new possibilities for automatic text extraction and layout recognition, automated image segmentation and annotation, as well as the analysis of visual sources and their contextualisation. At the same time, however, there is a lack of knowledge about how evidence – and subsequentially facts – are generated and how AI processes affect the attribution of authenticity to archival documents and photos. Currently, the humanities lack semantically high-quality, historically adequate and subject-appropriate training datasets. Similarly, there is hardly any agreement about what constitutes an acceptable outcome of computational classification processes, or what kind of benchmarks should be used to evaluate the results. We therefore need to develop best practices (that may tap into explainable Artificial Intelligence (XAI) methods), benchmarks and common goals. To increase the value that the information and knowledge held in our archives and collections have for future research, we need to deepen our understanding of processes and algorithms.
To deepen the discussion on these questions, the Research Lab ‘Digital Heuristics and Digital History’ of the Leibniz Research Alliance ‘Value of the Past’, in cooperation with NFDI4Memory, Task Area ‘Data Quality’ have organised a conference in Marburg on artificial intelligence in cultural heritage institutions, such as archives and collections, and how these new technologies are transforming archival institutional practices. Topics primarily focused on – but were not limited to – visual sources, such as photography and graphic collections or mixed image-text sources and multimodal information processing.
The conference provided a forum for researchers and practitioners from the humanities, as well as archives and collections to connect with researchers and engineers in the fields of artificial intelligence, computer science and the digital humanities, to discuss new findings, and to exchange experiences. The event was seeking to promote an interdisciplinary, cross-sectoral dialogue between research, development and practice.
The conference brought together curatorial and archiving knowledge and new AI-based methods but has also provided a forum for ethical reflection on the use of AI in academic and archival practices. Participants discussed how automated processing and AI methods require detailed epistemic reflection and methodological-technical control to ensure that no false or tainted evidence is generated. Thus, the conference reflected on the effects of these new technologies on the production of evidence, thereby contributing to the crucial question of how the digital transformation is changing knowledge creation in the humanities and what this means for scholarship in historical disciplines.
The call was met with a large response: Speakers from Austria, China, France, Germany, USA, UK and Sweden presented. More than 400 colleagues from 25 countries, most of them online, registered for the conference and followed the presentations or participated in the discussions. Papers covered topics such as Exploring and Analysing Collections from Textual and Multimodal Contexts, Computer Vision (Semantic Segmentation, Classification, Analysing and Understanding Images), The Effects of Computational Methods on Image Analytical Research and Visual Studies in Cultural Heritage, Opportunities and Challenges for the Automated Indexing and Cataloguing of Visual Sources in Archives and Collections.
As the organizers of the conference, we conclude from the high level of interest that – even though there are many possibilities in the various scientific communities to exchange upon new developments in AI – there is still a need for interdisciplinary and cross-sectoral exchange in the GLAM realm. We would like to keep this interest alive and support networking on the topic also in the time to come – not limited to conference participants.
Participants – and any colleague who likes to join – will be informed about future activities and about possible publications. We will keep you updated about future publications resulting from the conference. Stay tuned! As a start, we will publish several short summaries and elaborations on selected conference topics on this blog, written by young researchers who participated in the conference.
Programme and abstracts: https://www.herder-institut.de/event/conference-artificial-intelligence-in-archives-and-collections
Organizers:
Leibniz-Forschungsverbund „Wert der Vergangenheit“, Lab 1.3. Digitale Heuristik und Historik
Leibniz-Zentrum für Archäologie (LEIZA), Mainz
Herder-Institut für historische Ostmitteleuropaforschung – Institut der Leibniz-Gemeinschaft, Marburg
NFDI4Memory, Task Area Data Quality
This conference report was written by the organizing committee:
Elke Bauer, Herder-Institut
Simon Donig, Herder-Institut
Annette Frey, LEIZA
Dominik Kimmel, LEIZA
Further information on future activities on the topic: Interested parties can still use the conference registration tool to register for forthcoming information.
Contact: archivesai@herder-institut.de; dominik.kimmel@leiza.de
Title picture: image detail of the conference flyer
OpenEdition schlägt Ihnen vor, diesen Beitrag wie folgt zu zitieren:
Lab 1.3 Digitale Heuristik und Historik (20. Mai 2025). Artificial Intelligence in Archives and Collections: Practices, Potentials and Evidence Production in Dealing with Images and Multimodal Cultural Heritage. Value of the Past. Abgerufen am 10. November 2025 von https://doi.org/10.58079/13yki

Ein Gedanke zu „Artificial Intelligence in Archives and Collections: Practices, Potentials and Evidence Production in Dealing with Images and Multimodal Cultural Heritage“