Publications: 1. 'Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions', ACL 2025. 2. 'The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics', ACL 2023. 3. 'Architectural Sweet Spots for Modeling Human Label Variation by the Example of Argument Quality: It's Best to Relate Perspectives!', EMNLP 2023. Secured a MicroGrant by the German Society for Computational Linguistics.
Research Experience
Spent six weeks at the Computational Social Science department at GESIS, Leibniz Institute for the Social Sciences (Germany) in autumn 2024, working on an annotation framework to better capture relevant annotator background. Visited the MilaNLP Lab at Bocconi University (Italy) from April to June 2022, working on modelling socio-demographics for subjective tasks. Before joining the Semantic Computing Group, was an NLP solutions engineer and researcher (Prêt-à-LLOD) at AI startup Semalytix for two and a half years. Worked as a research assistant at the Chair of Digital Humanities at Paderborn University (Germany) for five months right after graduating. During his Master's, spent three months as a research intern at the Ubiquitous Knowledge Processing (UKP) Lab at TU Darmstadt (Germany).
Education
PhD in Computer Science, Bielefeld University (Germany), Semantic Computing Group. Advisor information not provided.
Background
Research Interests: Natural Language Processing (NLP) and Computational Social Science. Professional Field: Computer Science, Sociology, and Computational Linguistics. Brief Introduction: Focuses on modeling human label variation to learn better models from diverse annotators.