Carolin Schuster

M.Sc. (she/her)


Room: FMI 01.05.060
E-Mail: carolin.schuster(AT)tum.de
Address: TUM School of Computation, Information and Technology, Boltzmannstr. 3, 85748 Garching


Research Interests

  • Interpretability of Large Language Models
  • Semantics of Contextual Word Representations
  • Bias in Large Language Models
  • Word Embeddings for Social Research

Publications

Eichin, F., Schuster, C. M., Groh, G., and Hedderich, M. A. (2025). Semantic component analysis: Introducing multi-topic distributions to clustering-based topic modeling. In Findings of the Association for Computational Linguistics: EMNLP 2025 (forthcoming).

Schuster, C. M., Roman, M.-A., Ghatiwala, S., and Groh, G. (2025). Profiling bias in LLMs: Stereotype dimensions in contextual word embeddings. In Johansson, R. and Stymne, S., editors, Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 639–650, Tallinn, Estonia. University of Tartu Library.

Malberg, S., Poletukhin, R., Schuster, C., and Groh, G. (2025). A comprehensive evaluation of cognitive biases in LLMs. In Hämäläinen, M., Öhman, E., Bizzoni, Y., Miyagawa, S., and Alnajjar, K., editors, Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities, pages 578–613, Albuquerque, USA. Association for Computational Linguistics.

Chen, D., Satish, A., Khanbayov, R., Schuster, C., and Groh, G. (2025). Tuning into bias: A computational study of gender bias in song lyrics. In Kazantseva, A., Szpakowicz, S., Degaetano-Ortlieb, S., Bizzoni, Y., and Pagel, J., editors, Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025), pages 117–129, Albuquerque, New Mexico. Association for Computational Linguistics.

Falkenstein, J., Schuster, C. M., Berger, A. H., and Groh, G. (2024). From language to pixels: Task recognition and task learning in LLMs. In Hupkes, D., Dankers, V., Batsuren, K., Kazemnejad, A., Christodoulopoulos, C., Giulianelli, M., and Cotterell, R., editors, Proceedings of the 2nd GenBench Workshop on Generalisation (Benchmarking) in NLP, pages 27–41, Miami, Florida, USA. Association for Computational Linguistics.


Supervision of Theses / Guided Research

There are no further topics available.