Academic Interests
Hannah is particularly interested in the ethical side of large language models as well as social biases and the explainability behind them. Outside of NLP, her academic interests range from social inequality and discrimination to quantitative research methodology including surveys and computational text analysis.
Background
Hannah has a bachelor's degree in Political Science and Sociology from the University of Göttingen and a master's degree in Social Data Science from the University of Copenhagen. During her studies, she focused on the quantitative analysis of social media data as well as gender bias in LLMs. Moreover, Hannah worked in multiple research projects within sociology, diversity research, and gender studies particularly focusing on research methodology.
PhD project
Benchmarking Ethical Reasoning in Large Language Models
The project combines NLP and philosophy aiming at developing a benchmarking methodology for machine ethics in LLMs. A particular focus lies on the evaluation of moral judgments by LLMs.