Continuous context sampling allows extending diversity boundaries of large language models
Mateusz Bystroński, Nitesh Chawla, Tomasz Kajdanowicz, Doheon Han
Kerrville, TX : Association for Computational Linguistics, cop. 2026. s. 1436-1450.
2026
Profil
Mateusz Bystroński
Doktorant
Grupy badawcze
Publikacje(5)
Factual state discovery benchmark: evaluating fact elicitation in Polish tax law
Mateusz Bystroński, Kamil Tagowski, Denis P Janiak, Julia Farganus, Łukasz M Augustyniak, Tomasz Kajdanowicz, Monika Kajdanowicz
Kerrville, TX : Association for Computational Linguistics, cop. 2026. s. 1262-1279.
2026
Beyond discrete search: divergent thinking as intention optimization in latent space
Mateusz Bystroński, Grzegorz A Piotrowski, Tomasz Kajdanowicz
Kerrville, TX : Association for Computational Linguistics, cop. 2026. s. 1007-1016.
2026
A multi-stage LLM framework for generating realistic synthetic medical datasets
Mikołaj Hołysz, Mateusz Bystroński, Grzegorz A Piotrowski, Grzegorz Chodak, Tomasz Kajdanowicz
[Atlanta : Association for Information Systems, 2025]. s. 1-5.
2025
When will the tokens end? Graph-based forecasting for LLMs output length
Grzegorz A. Piotrowski, Mateusz Bystroński, Mikołaj Hołysz, Jakub Binkowski, Grzegorz Chodak, Tomasz Kajdanowicz
Kerrville, TX : Association for Computational Linguistics, cop. 2025. s. 843-848.
2025