Ewelina Gajewska has completed a master's degree in cognitive science at Adam Mickiewicz University. During her master's studies she was a research assistant in international and National Science Centre funded projects (Volkswagen Stiftung, SONATA) working on computational modelling of arguments in natural language. Since 2023 Ewelina is a PhD student in Laboratory of The New Ethos at Warsaw University of Technology as part of the international iTRUST (CHIST-ERA) project, focusing on machine learning, natural language processing and social media analytics in the context of argumentative conflict, hateful language and social polarisation.

Newest publications:

Gajewska, E., Budzynska, K., & Chudziak, J. A. (2026). Improving Implicit Hate Speech Detection via a Community-Driven Multi-Agent Framework. In Proceedings of the 18th International Conference on Agents and Artificial Intelligence - Volume 1. ISBN 978-989-758-796-2, ISSN 2184-433X (pp. 559-566). DOI 10.5220/0014434500004052

Gajewska, E., Derbent, A., Chudziak, J. A., & Budzynska, K. (2026). Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detection. In 59th Hawaii International Conference on System Sciences (HICSS-59) (pp. 6644-6653). https://hdl.handle.net/10125/112188