Sebastian Bordt

Hi there! I'm a postdoctoral researcher interested in large language models and interpretability. I work in the theory of machine learning group at the University of Tübingen, supervised by Ulrike von Luxburg.

Currently, I'm very interested in a systematic understanding of pre-training. For a flavor of how I think this can look like, consider this ICML'25 paper. Before that, I did a number of black-box evaluations of LLMs, see here, here, or here. At Microsoft Research, we did some experiments with GPT-4 and GAMs in a healthcare setting.

During my PhD, I worked on a variety of different topics in explainable machine learning. For example, I have worked on the connections between post-hoc methods and interpretable models, and on the suitability of explanation algorithms for regulation. If you are interested in these topics, take a look at this blog post.

Prior to my work in machine learning, I obtained Master's degrees in Mathematics and Economics at TUM and LMU in Munich. I also spent some time at the Munich Graduate School of Economics.