Publikacje

Attention sinks as internal signals for hallucination detection in large language models

Jakub Binkowski, Kamil Adamczewski, Tomasz Kajdanowicz

Proceedings of the 43rd International Conference on Machine Learning, Seoul, South Korea, 6th-11th July 2026 · 2026

Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety

Denis P. Janiak, Julia A Moska, Dawid Motyka, Paweł T Walkowiak, Arkadiusz Janz, Karolina Seweryn, Bartosz Żuk

The 19th Conference of the European Chapter of the Association for Computational Linguistics · 2026

FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs

Albert K. Sawczyn, Jakub Binkowski, Denis P Janiak, Tomasz Kajdanowicz, Bogdan Gabrys

EACL 2026 · 2026

Initial study on cancer diagnosis using AI/NLP and expert system integration

Mariusz Pelc, Tomasz Kajdanowicz, Aleksandra D Kawala-Sterniuk, Sławomir Stemplewski, Waldemar Bauer

ICCS 2026 · 2026

Beyond discrete search: divergent thinking as intention optimization in latent space

Mateusz Bystroński, Grzegorz A Piotrowski, Tomasz Kajdanowicz

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) · 2026

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

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) · 2026

Continuous context sampling allows extending diversity boundaries of large language models

Mateusz Bystroński, Nitesh Chawla, Tomasz Kajdanowicz, Doheon Han

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) · 2026

Braves-Cog: An integrated multimodal framework for biomarker-guided cognitive neuromodulation

Karolina Fila-Pawłowska, Joanna K Budzisz, Magdalena Kasprowicz, Marta A Rusnak, Agnieszka Kazimierska, Agnieszka M Uryga, Aleksandra D Kawala-Sterniuk, Tomasz Kajdanowicz, Joanna A Rymaszewska

2026 · 2026

A geometry-based view of Mahalanobis OOD detection

Denis P. Janiak, Jakub Binkowski, Tomasz Kajdanowicz

Proceedings of the 43rd International Conference on Machine Learning, Seoul, South Korea, 6th-11th July 2026 · 2026

Methods for multi-object representation learning in images and videos

Piotr Zieliński

2026

Wykorzystanie sieci neuronowych w przetwarzaniu danych metabolomicznych opartych na spektroskopii NMR

Natalia Herda, Mateusz Bystroński, Piotr Młynarz, Tomasz Kajdanowicz

Chemik · 2026

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

The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) · 2025

Multimodal Machine Learning Analysis of fNIRS Signals Using LSTM and KNN Models for Cognitive States and Brain Activation Patterns Prediction

Tomasz Kajdanowicz, Mariusz Pelc, Aleksandra D Kawala-Sterniuk, Adrian Luckiewicz, Dariusz Mikołajewski, Radosław Roszczyk, Krzysztof Siwek, Piotr Sterniuk, Edward Jacek Gorzelanczyk

ACIIDS 2025 · 2025

Implementation of convolutional neural networks for the purpose of five types of white blood cells automatic counting

Tomasz Kajdanowicz, Aleksandra D Kawala-Sterniuk, Grzegorz Drałus, Damian Mazur, Konrad Łukiewicz, Michał Podpora, Jacek Bartman, Henryk Racheniuk

ICCS 2025 · 2025

Typology of image crises using large language models: a novel approach to crisis classification

Grzegorz Chodak, Aleksander P Szczęsny, Przemysław Kazienko, Oliwier Kaszyca, Marcin Ł Oleksy, Mateusz Kochanek, Dominika Szydło, Igor Cichecki, Wiktoria M Mieleszczenko-Kowszewicz, Ewa Dzięcioł, Tomasz Kajdanowicz, Maciej Piasecki, Jan Kocoń, Dariusz Tworzydło, Kajetan Bilski, Kaja Matuszak, Przemysław Palacz

Journal of Contingencies and Crisis Management · 2025

The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs

Denis P. Janiak, Jakub Binkowski, Albert K Sawczyn, Tomasz Kajdanowicz, Bogdan Gabrys, Ravid Shwartz-Ziv

The 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, November 4-9 · 2025

Hallucination Detection in LLMs Using Spectral Features of Attention Maps

Jakub Binkowski, Denis P Janiak, Albert K Sawczyn, Tomasz Kajdanowicz, Bogdan Gabrys

The 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, November 4-9 · 2025

Identifying super spreaders in multilayer networks

Michał Czuba, Stolarski, Mateusz, Adam Piróg, Piotr Bielak, Piotr Bródka, Mateusz Stolarski

14th Conference on Prestigious Applications of Intelligent Systems (PAIS 2025) · 2025

A multi-stage LLM framework for generating realistic synthetic medical datasets

Mikołaj Hołysz, Mateusz Bystroński, Grzegorz A Piotrowski, Grzegorz Chodak, Tomasz Kajdanowicz

Association for Information Systems · 2025

Towards weight-space interpretation of Low-Rank Adapters for Diffusion Models

Jacek J. Duszenko, Piotr Bielak

ICCS 2025 · 2025