Katharina (she/her) is a doctoral researcher in the Tustworthy AI Lab at the University of Hamburg supervised by Prof. Dr. Anne Lauscher and Dr. Jae Hee Lee. Her PhD work focuses on making multi-agent systems fairer.

She holds an M.Sc. in Language Science and Technology at Saarland University, where her thesis established a mechanistic understanding of pronoun reuse under discourse complexity. Beyond this, she has worked and published in the intersection of mechanistic interpretability and multilinguality and political biases.

Katharina's personal website: https://katharinatrinley.github.io/ 

Katharina's current research interests include:

• Multi-Agent Systems
• Mechanistic Interpretability
• Fairness and Bias
• Multilinguality