Maxime Dassen

Hi, I'm Maxime (she/her). I am a PhD student in Artificial Intelligence at the IRLab of the University of Amsterdam, advised by Andrew Yates and Evangelos Kanoulas. I'm a researcher interested in how language and vision-language models coordinate what they observe with what they know; when they trust external evidence, when they shouldn't, and what their internal computation tells us about the difference. My work sits across retrieval-augmented systems, multimodal grounding, and trustworthy AI, with the goal of building models people can actually rely on.

In 2025 I was a Visiting PhD Student at the Johns Hopkins University HLTCOE as part of the SCALE 2025 program, and will return for SCALE 2026 to work on multimodal RAG.

Selected Research

I'm interested in machine learning, deep learning, generative AI, and multimodal learning. 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%.

Template adjusted from this website.