Tomasz Limisiewicz

31 papers A* 3Journal 18Unranked 10
YearRankTypeTitle / Venue / Authors
2025 — conf
Beyond Literal Token Overlap: Token Alignability for Multilinguality.
NAACL (Short Papers)
Katharina Hämmerl, Tomasz Limisiewicz, Jindrich Libovický, Alexander Fraser
2025 J jnl
Beyond Literal Token Overlap: Token Alignability for Multilinguality.
CoRR
Katharina Hämmerl, Tomasz Limisiewicz, Jindrich Libovický, Alexander Fraser
2025 J jnl
Bolmo: Byteifying the Next Generation of Language Models.
CoRR
Benjamin Minixhofer, Tyler Murray, Tomasz Limisiewicz, Anna Korhonen, Luke Zettlemoyer, Noah A. Smith, Edoardo M. Ponti, Luca Soldaini, Valentin Hofmann
2025 J jnl
Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation.
CoRR
Tomasz Limisiewicz, David Marecek, Tomás Musil
2024 A* conf
Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models.
EMNLP
Terra Blevins, Tomasz Limisiewicz, Suchin Gururangan, Margaret Li, Hila Gonen, Noah A. Smith, Luke Zettlemoyer
2024 J jnl
Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models.
CoRR
Terra Blevins, Tomasz Limisiewicz, Suchin Gururangan, Margaret Li, Hila Gonen, Noah A. Smith, Luke Zettlemoyer
2024 A* conf
Debiasing Algorithm through Model Adaptation.
ICLR
Tomasz Limisiewicz, David Marecek, Tomás Musil
2024 A* conf
MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization.
NeurIPS
Orevaoghene Ahia, Sachin Kumar, Hila Gonen, Valentin Hofmann, Tomasz Limisiewicz, Yulia Tsvetkov, Noah A. Smith
2024 J jnl
MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization.
CoRR
Orevaoghene Ahia, Sachin Kumar, Hila Gonen, Valentin Hoffman, Tomasz Limisiewicz, Yulia Tsvetkov, Noah A. Smith
2024 — conf
MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling.
ACL (1)
Tomasz Limisiewicz, Terra Blevins, Hila Gonen, Orevaoghene Ahia, Luke Zettlemoyer
2024 J jnl
MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling.
CoRR
Tomasz Limisiewicz, Terra Blevins, Hila Gonen, Orevaoghene Ahia, Luke Zettlemoyer
2024 J jnl
Teaching LLMs at Charles University: Assignments and Activities.
CoRR
Jindrich Helcl, Zdenek Kasner, Ondrej Dusek, Tomasz Limisiewicz, Dominik Machácek, Tomás Musil, Jindrich Libovický
2023 J jnl
Debiasing Algorithm through Model Adaptation.
CoRR
Tomasz Limisiewicz, David Marecek, Tomás Musil
2023 — conf
Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation.
IJCNLP (1)
Bar Iluz, Tomasz Limisiewicz, Gabriel Stanovsky, David Marecek
2023 J jnl
Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation.
CoRR
Bar Iluz, Tomasz Limisiewicz, Gabriel Stanovsky, David Marecek
2023 — conf
Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages.
ACL (Findings)
Tomasz Limisiewicz, Jirí Balhar, David Marecek
2023 J jnl
Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages.
CoRR
Tomasz Limisiewicz, Jirí Balhar, David Marecek
2022 — conf
A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank.
NAACL-HLT
Dan Malkin, Tomasz Limisiewicz, Gabriel Stanovsky
2022 J jnl
A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank.
CoRR
Dan Malkin, Tomasz Limisiewicz, Gabriel Stanovsky
2022 J jnl
Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information.
CoRR
Tomasz Limisiewicz, David Marecek
2022 J jnl
You Can Have Your Data and Balance It Too: Towards Balanced and Efficient Multilingual Models.
CoRR
Tomasz Limisiewicz, Dan Malkin, Gabriel Stanovsky
2021 — conf
Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes.
EMNLP (1)
Tomasz Limisiewicz, David Marecek
2021 J jnl
Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes.
CoRR
Tomasz Limisiewicz, David Marecek
2021 — conf
Introducing Orthogonal Constraint in Structural Probes.
ACL/IJCNLP (1)
Tomasz Limisiewicz, David Marecek
2020 — conf
Gender Coreference and Bias Evaluation at WMT 2020.
WMT@EMNLP
Tom Kocmi, Tomasz Limisiewicz, Gabriel Stanovsky
2020 J jnl
Gender Coreference and Bias Evaluation at WMT 2020.
CoRR
Tom Kocmi, Tomasz Limisiewicz, Gabriel Stanovsky
2020 J jnl
Introducing Orthogonal Constraint in Structural Probes.
CoRR
Tomasz Limisiewicz, David Marecek
2020 — conf
Syntax Representation in Word Embeddings and Neural Networks - A Survey.
ITAT
Tomasz Limisiewicz, David Marecek
2020 J jnl
Syntax Representation in Word Embeddings and Neural Networks - A Survey.
CoRR
Tomasz Limisiewicz, David Marecek
2020 — conf
Universal Dependencies according to BERT: both more specific and more general.
EMNLP (Findings)
Tomasz Limisiewicz, David Marecek, Rudolf Rosa
2020 J jnl
Universal Dependencies according to BERT: both more specific and more general.
CoRR
Tomasz Limisiewicz, Rudolf Rosa, David Marecek