About me
My name is Kathy; I am a fourth-year PhD student in Computational Linguistics at CIS. I'm supervised by Alex Fraser (TUM Heilbronn) and mentored by Jindřich Libovický (Charles University, Prague).
My research interests are multilingual language models, cross-lingual transfer, and how they function, as well as sociotechnical aspects such as the cultural contexts in which models are deployed.
I'm affiliated with and supported by the Munich Center for Machine Learning, and I recently went on a research visit to Prague.
Between autumn 2018 and spring 2021, I obtained my Master's degree from CIS. Before that, I studied English Philology and Computer Science for my undergrad.
Room: L149 at CIS.
Publications
Katharina Hämmerl, Tomasz Limisiewicz, Jindřich Libovický, and Alexander Fraser. 2025.
Beyond Literal Token Overlap: Token Alignability for Multilinguality. To be published at NAACL 2025.Katharina Hämmerl, Andrei-Alexandru Manea, Gianluca Vico, Jindřich Helcl, and Jindřich Libovický. 2024.
CUNI and LMU Submission to the MRL 2024 Shared Task on Multi-lingual Multi-task Information Retrieval. MRL 2024.Katharina Hämmerl, Jindřich Libovický, and Alexander Fraser. 2024.
Understanding Cross-Lingual Alignment---A Survey. Findings of ACL 2024.Felix Friedrich, Katharina Hämmerl, Patrick Schramowski, Manuel Brack, Jindrich Libovicky, Kristian Kersting, and Alexander Fraser. 2024.
Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You (preprint). arXiv:2401.16092 [cs.CL]Marion Di Marco, Katharina Hämmerl, and Alexander Fraser. 2023.
A Study on Accessing Linguistic Information in Pre-Trained Language Models by Using Prompts. EMNLP 2023.Katharina Hämmerl, Alina Fastowski, Jindřich Libovický, and Alexander Fraser. 2023.
Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity.
Findings of ACL 2023.Katharina Hämmerl, Björn Deiseroth, Patrick Schramowski, Jindřich Libovický, Constantin Rothkopf, Alexander Fraser, and Kristian Kersting. 2023. Speaking Multiple Languages Affects the Moral Bias of Language Models. Findings of ACL, 2023.
Katharina Hämmerl, Jindřich Libovický, and Alexander Fraser. 2022.
Combining Static and Contextualised Multilingual Embeddings. Findings of ACL 2022.Katharina Hämmerl, Björn Deiseroth, Patrick Schramowski, Jindřich Libovický, Alexander Fraser, and Kristian Kersting. 2022.
Do Multilingual Language Models Capture Differing Moral Norms? (preprint) arXiv:2203.09904 [cs.CL]
Selected Students
- Yuting ZHAO. 2023.
Adaptation of Transformer-based models for Swiss German Dialects. (Master's thesis CL) - Alina Fastowski. 2022.
Rogue Dimensions in Multilingual Embeddings: The Influence of Outliers on Similarity Search (Master's thesis CL)