Talks
A selection of invited and contributed talks.
Invited Talks
2026
Understanding LLMs for Science: From Benchmarks to Mechanisms
LT3 Language and Translation Technology Team
Ghent LT3 Language and Translation Technology Team
Does Mechanistic Interpretability Really Open the Black Box?
Radboud University
Nijmegen Radboud University
Ethical and Epistemic Challenges of Agentic GenAI in Research
EOSC-ARENA project kickoff, June 2026
Poznań EOSC-ARENA project kickoff, June 2026
2025
When AI Becomes the Theorist
Computing Challenges and AI Opportunities for Future Colliders workshop
Geneva Computing Challenges and AI Opportunities for Future Colliders workshop
Selected Effect Functions in GenAI Artefacts
University of Cincinnati
Cincinnati, USA University of Cincinnati
The New Science of Artificial Intelligence
Purdue University
Purdue, USA Purdue University
Mechanistic Interpretability for AI Safety: It's Time to Open the Black Box
Butler University
Indianapolis, USA Butler University
2024
Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?
Allianz Onderzoek Seminar
Ghent Allianz Onderzoek Seminar
Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?
Institute for Science in Society Colloquium
Nijmegen Institute for Science in Society Colloquium
IBE in XAI
Allianz Onderzoek Seminar
Brussels Allianz Onderzoek Seminar
The Understanding Benchmark
Lorentz Workshop
Leiden Lorentz Workshop
2023
Machine Learning in Physics
Radboud University
Nijmegen Radboud University
The Scientific Understanding Test
Institute for Science in Society Colloquium
Nijmegen Institute for Science in Society Colloquium
How Large Language Models Increase Scientific Understanding in Physics
IMAPP Seminar
Nijmegen IMAPP Seminar
The Understanding Test
Hybrid Workshop on the Philosophy of Large Language Models
Eindhoven Hybrid Workshop on the Philosophy of Large Language Models
2019 - 2022
AI and Machine-Learning Technology
University of Twente, PSTS Master Course
Twente, 2022 University of Twente, PSTS Master Course
On Explanation in the Engineering Sciences
HPS Colloquium, Ruhr-Universität Bochum
Bochum, 2021 HPS Colloquium, Ruhr-Universität Bochum
Appointed Commentator at ALO Seminars, Ghent University
On Uskali Mäki (2019), Francesco Guala (2021), and Mieke Boon (2021)
On Uskali Mäki (2019), Francesco Guala (2021), and Mieke Boon (2021)
Contributed Talks
| Year | Venue | Title |
|---|---|---|
| 2026 | APSA (Asian Philosophy of Science Association), Singapore | What is Mechanistic in Mechanistic Interpretability? |
| 2026 | SPSP, Cambridge | What is Mechanistic in Mechanistic Interpretability? |
| 2025 | EPSA, Groningen | Optimality Explanations & Common Causes |
| 2025 | EPSA, Groningen poster | Pluralistic RLHF: Leveraging Philosophy of Science and Social Epistemology to Improve Large Language Models |
| 2023 | PhAI, Erlangen | Inference to the Best Explanation in Explainable AI |
| 2023 | EPSA, Belgrade | Measuring Understanding in Humans and Machines |
| 2023 | IACAP, Prague | Benchmarking Understanding of LLMs |
| 2022 | SPSP, Ghent | Evaluating Accident Causation Models in Engineering Science |
| 2022 | Mathematics as Science, Ghent | Task-based 'Distinctively' Mathematical Explanations Do Not Address Physical Facts |
| 2022 | Mechanisms in Ghent | An Account of Fictional Mechanisms by Constraint |
| 2021 | EPSA, Turin | Explanatory Holes? Testing the Limits of the Mechanistic Framework |
| 2019 | OZSW, Tilburg University | IBE in Engineering Science: The Case of Malfunction Explanation |