Publications
2026
EMNLP WildSEEK: Evaluating Language Models for Information-Seeking Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), Budapest, Hungary arXiv Website 🤗
FAccT Democratizing News Recommenders: Modeling Multiple Perspectives for News Candidate Generation with VQ-VAE Proceedings of the ACM Conference on Fairness, Accountability, and Transparency (FAccT), Montreal, Canada ACM
EACL Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Rabat, Morocco ACL Anthology
Preprint What Is The Political Content in LLMs’ Pre-and Post-Training Data? Preprint, arXiv:2509.22367 arXiv 🤗
Preprint Structuring the Space of Perspectives Preprint arXiv
2025
*SEM Generalizability of Media Frames: Corpus creation and analysis across countries Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM), co-located with EMNLP, Suzhou, China ACL Anthology Data
INRA Leveraging Media Frames to Improve Normative Diversity in News Recommendations Proceedings of the 13th International Workshop on News Recommendation and Analytics, co-located with RecSys 2025, Prague, Czech Republic CEUR
PhD Thesis Methods for mining political opinions from texts and large language models PhD Thesis, University of Stuttgart PDF
2024
TACL Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs Transactions of the Association for Computational Linguistics (TACL), volume 12 MIT Press Direct 🤗
EMNLP Findings Toeing the Party Line: Election Manifestos as a Key to Understand Political Discourse on Twitter Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6115–6130, Miami, Florida, USA ACL Anthology
RATIO Automatic Analysis of Political Debates and Manifestos: Successes and Challenges Proceedings of the 1st International Conference on Recent Advances in Robust Argumentation Machines (RATIO-24), Springer Nature Springer
2023
EMNLP Multilingual estimation of political-party positioning: From label aggregation to long-input Transformers Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9497–9511, Singapore ACL Anthology
ACL Findings Additive manifesto decomposition: A policy domain aware method for understanding party positioning Findings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pages 7874–7890, Toronto, Canada ACL Anthology
2022
CoNLL Optimizing text representations to capture (dis)similarity between political parties Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL), pages 325–338, Abu Dhabi, United Arab Emirates (Hybrid) ACL Anthology
SustaiNLP Algorithmic Diversity and Tiny Models: Comparing Binary Networks and the Fruit Fly Algorithm on Document Representation Tasks Proceedings of the Third Workshop on Simple and Efficient Natural Language Processing (SustaiNLP), pages 17–28, Abu Dhabi, United Arab Emirates (Hybrid) ACL Anthology
CPSS Why justifications of claims matter for understanding party positions Proceedings of the 2nd Workshop on Computational Linguistics for Political Text Analysis CPSS
2021
- CLEF Exploiting Contextualized Word Representations to Profile Haters on Twitter CLEF (Working Notes), pages 1871–1882 CEUR