PhD
Chair of Statistics and Data Science for Social Sciences and the Humanities at LMU
Institut für Statistik
Ludwigstr. 33
80539 München
Biosketch
Tobias Holtdirk is a PhD candidate at the Social Data Science and AI Lab (SODA) at the Institute of Statistics, LMU Munich, which he joined in 2025, and a junior member of the Munich Center for Machine Learning (MCML). His research focuses on applications of natural language processing in the social sciences, in particular on large language models for public opinion research and social simulation. Before joining LMU, he spent a year as a research associate in the Department of Computational Social Science at GESIS – Leibniz Institute for the Social Sciences in Cologne. He holds a B.Sc. in Computer Science with a minor in Philosophy and an M.Sc. in Computational Social Systems, both from RWTH Aachen University.
relAI Research
His research applies large language models to public opinion research and social simulation. He is especially interested in evaluation and benchmarking: measuring how well LLMs represent the opinions of real populations, where they show biases, and how they can be combined with survey data to produce reliable results.
More broadly, he is interested in applications of NLP in the social sciences, from supporting questionnaire design, data collection, and annotation to automatically assessing the reproducibility of published research. These applications can make research faster and less burdensome for respondents, but they also raise methodological and ethical challenges, such as validity, bias, and privacy concerns.