Recent developments in Artificial Intelligence (AI) and Large Language Models (LLM) in particular have disrupted the way we interact with information. The well-annotated and structured data in digital repositories provide valuable input for developing AI models and make the information available to more people in an interconnected way. In this webinar, we discuss (1) use-cases on how to add value to data in digital repositories by using AI technologies, (2) important concepts of LLMs and (3) how the EOSC Data Commons project supports data discovery using AI. We will conclude with two parallel sessions. One session will be a discussion, in which we aim to define the most interesting opportunities and pressing challenges. The second parallel session will be a tutorial with an example on how to make use of repository data with LLM.
Speakers:
Séverine Duvaud, SIB Swiss Institute of Bioinformatics, Team lead biodata resources
Ana-Claudia Sima, SIB Swiss Institute of Bioinformatics, Co-Team Lead, Knowledge Representation Unit
Geert van Geest, SIB Swiss Institute of Bioinformatics, Training Project Manage
Date: 2nd of December, 2025
Time (CET/CEST): 15:00 - 16:30
Agenda
Below you will find the planned agenda for the workshop. The second half of the session will be divided into two break out rooms, for further discussions on topics of interest for the participants.
| Timing | Topic | Speaker |
|---|---|---|
| 15:00-15:15 | Opportunities for AI in digital repositories - a use case | Séverine Duvaud |
| 15:15-15:45 | Introduction to Large Language Models in the context of digital repositories | Ana-Claudia Sima |
| 15:45-16:00 | AI-based metadata discovery - aims and activities in the EOSC data commons Project | Ana-Claudia Sima |
| 16:00-16:30 | (Parallel) Structured discussion with conclusions | Geert van Geest |
| 16:00-16:30 | (Parallel) Tutorial on leveraging LLMs for repositories | Ana-Claudia Sima |