| 2025 | INLG | Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation. | Tomasz Limisiewicz, David Marecek, Toms Musil |
| 2025 | NAACL | Beyond Literal Token Overlap: Token Alignability for Multilinguality. | Katharina Hmmerl, Tomasz Limisiewicz, Jindrich Libovick, Alexander Fraser |
| 2024 | ACL | MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling. | Tomasz Limisiewicz, Terra Blevins, Hila Gonen, Orevaoghene Ahia, Luke Zettlemoyer |
| 2024 | EMNLP | Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models. | Terra Blevins, Tomasz Limisiewicz, Suchin Gururangan, Margaret Li, Hila Gonen, Noah A. Smith, Luke Zettlemoyer |
| 2024 | ICLR | Debiasing Algorithm through Model Adaptation. | Tomasz Limisiewicz, David Marecek, Toms Musil |
| 2023 | ACL | Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages. | Tomasz Limisiewicz, Jir Balhar, David Marecek |
| 2023 | IJCNLP | Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation. | Bar Iluz, Tomasz Limisiewicz, Gabriel Stanovsky, David Marecek |
| 2022 | NAACL | A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank. | Dan Malkin, Tomasz Limisiewicz, Gabriel Stanovsky |
| 2021 | ACL | Introducing Orthogonal Constraint in Structural Probes. | Tomasz Limisiewicz, David Marecek |
| 2021 | EMNLP | Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes. | Tomasz Limisiewicz, David Marecek |
| 2020 | EMNLP | Universal Dependencies according to BERT: both more specific and more general. | Tomasz Limisiewicz, David Marecek, Rudolf Rosa |