I am currently pursuing an M.A. in Computational Linguistics at Heidelberg University, where I also work as a research assistant in the Department of German Language and Literature. My work applies computational linguistic methods, including dataset creation, model evaluation, and interpretability, to interdisciplinary research projects in the digital humanities and beyond.

Previously, I obtained my B.A. in Computational Linguistics from Heidelberg University under the supervision of Prof. Dr. Anette Frank. My bachelor’s thesis, Interpreting Failures of Multimodal Reasoning in Vision-Language Models, investigated reasoning failures in vision-language models using interpretability methods.

My primary research interests center around NLP, with a focus on interpretability, Responsible AI, and AI safety. I am particularly interested in developing methods to better understand and evaluate large language models and vision-language models, with the goal of improving their transparency, reliability, and trustworthiness.