About

Jelle Zuidema

Jelle Zuidema

Associate Professor

Visit personal website

Jelle Zuidema is Associate Professor of Natural Language Processing, Explainable AI and Cognitive Modelling at the ILLC. He studied artificial intelligence in Utrecht (1993-2000), worked at the Sony Computer Science Laboratory-Paris and the Free University Brussels, obtained a PhD at the University of Edinburgh (2005), and did postdocs in Amsterdam and Leiden. With his PhD and MSc students, he did pioneering work in deep learning for NLP and interpretability methods for Large Language Models.

Language models White

Bias White

Explainable White

Research projects of the researcher

Below you can find a sample of the CERTAIN-related research projects of this researcher.

InDeep: Interpreting Deep Learning Models for Text and Sound

Goal of the project is to find ways to make popular Artificial Intelligence models for language, speech and music more explainable.

Explainable White

Theory-driven White

Ongoing

Improving Language Model Bias Measures

Many researchers develop tools for measuring how biased language models are; in this project we work on improving these tools

Language models White

Bias White

Theory-driven White

Ongoing

Papers by the researcher

Let's treat language model tests as professionally as we treat exams

Language models Plum

Bias Plum

Theory-driven Plum

Quantifying Context Mixing in Transformers

Language models Plum

Explainable Plum

Theory-driven Plum

Can NLP bias measures be trusted?

Language models Plum

Bias Plum

Theory-driven Plum