📅 27 November 2025
📍 Vrije Universiteit Amsterdam (exact room TBA) – no hybrid option available
🕘 09:00-12:00 and 13:00-17:00
💸 Fee: free! but registration is required (limited places)
📝 You have to register for the separate sessions described below (scroll down on these links and click “Aanmelden”). You do not have to attend both but if you’d like to, you have to register for both!
- Morning session 09:00-12:00 (theoretical): https://ivdnt.org/evenement/workshop-llms-1/
- Afternoon session 13:00-17:00 (practical): https://ivdnt.org/evenement/workshop-llms-2/
Large Language Models (LLMs) are transforming how we can approach research in the social sciences and humanities. But alongside their generalization power come serious methodological considerations. In this full-day workshop in the scope of Task 3.1 of the SSHOC-NL project we will first learn more from three speakers in the morning session about the capabilities and pitfalls of LLMs, how they work and how they can be evaluated. Then, in the afternoon session, we will use named entity recognition (NER) as a use-case to see how LLMs might assist us in improving a baseline NER model by generating additional, synthetic training material. We will make use of historical data. While the use-case itself only serves as an example, the methodology used (expanding training data with LLMs, evaluating and comparing a base model to an improved model) can be applied broadly to different topics and fields.
💡 Target audience
This workshop is explicitly targeted towards researchers in humanities and social sciences. The first session does not require any prior knowledge. The second session in the afternoon is hands-on and technical where we will run through a prepared notebook on Google Colab together (so you will need an account on https://colab.google/). Experience with Python and Jupyter notebooks is recommended for this second part.
📅 Programme
Subject to change
9:30-9:45: welcome + SSHOC Task 3.1 introduction (Ellie Smith)
9:45-10:20: The Ins and Outs of LLMs (Antske Fokkens)
10:20-10:50: coffee break
10:50-11:25: Title to be confirmed (Stella Verkijk)
11:25-12:00: What is a “good” LLM? Common evaluation tasks for LLMs (Bram Vanroy)
12:00-13:30: lunch (only provided for those that registered for the full day)
13:30-15:00: hands-on session part 1
15:00-15:30: coffee break
15:30-17:00: hands-on session part 2
🎈 Contact
The workshop is organized by the Vrije Universiteit Amsterdam (VU) and the Instituut voor de Nederlands Taal (INT) as part of SSHOC-NL Task 3.1: Methodologically Sound Data Enrichment and Evaluation. You can contact us via this website.
Geef een reactie