|
Maxime Dassen I am a PhD student in Artificial Intelligence at the IRLab of the University of Amsterdam, advised by Andrew Yates and Evangelos Kanoulas. My research interests lie in Multimodal NLP, RAG, and Mechanistic Interpretability. I am particularly interested in bridging technical model mechanisms with human-centric behavioral outcomes to build accessible and ethical AI. During my MScs, I completed internships at PwC and ASML. In the summer of 2025, I was a research visitor at the Johns Hopkins University HLTCOE as part of the SCALE program, and will return for SCALE 2026 to work on Multimodal RAG.
|
|
Selected ResearchI'm interested in machine learning, deep learning, generative AI, natural language processing, and information retrieval. Some papers are highlighted. |
ECIR '2026
|
FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG
Maxime Dassen, Rebecca Kotula, Kenton Murray, Andrew Yates, Dawn Lawrie, Efsun Kayi, James Mayfield, Kevin Duh European Conference on Information Retrieval (ECIR), 2026 arXiv code We introduce FACTUM, a mechanistic framework that detects citation hallucinations in long-form RAG by identifying scale-dependent signatures in transformer pathways, outperforming state-of-the-art baselines by up to 37.5%. |
Miscellanea |
Teaching |
Supervising MScs theses of MSc AI and MSc Data Science students at the University of Amsterdam.
Teaching Assistant for Information Retrieval 1. |
Academic Service |
Managing the IRLab LinkedIn page, focusing on digital presence and research outreach for the lab.
|
|
Template adjusted from this website. |