I am a PhD candidate in computational linguistics at Heinrich-Heine University (HHU) under the supervision of Prof. Dr. Laura Kallmeyer and Dr. Rainer Osswald. At the same time, I work as a doctoral researcher at the DFG-funded project “Coercion and Copredication as Flexible Frame Composition”.

I am interested in representation learning and understanding the representations of Large Language Models, with a particular focus on their capacity to handle semantic productivity.

Topics I have worked on:

• Lexical ambiguity
• Interpretability of language model representations
• Learning invariant representations via adversarial forgetting