Katarzyna Lorenc
Research interests: Artificial Intelligence, Natural Language Processing, AI Safety
Katarzyna Lorenc is a specialist in natural language processing (NLP), with a strong focus on large language models (LLMs). Her expertise encompasses the alignment of generative models, safety evaluation, and resilience testing against adversarial attacks. She also oversees the filtering of model-generated responses to ensure compliance with ethical standards and safety protocols. Katarzyna holds a degree in mathematics from the Warsaw University of Technology, specializing in Statistics and Data Analysis.
Selected Publications
Articles
Karolina Seweryn, Anna Kołos, Agnieszka Karlińska, Katarzyna Lorenc, Katarzyna Dziewulska, Maciej Chrabaszcz, Aleksandra Krasnodebska, Paula Betscher, Zofia Cieślińska, Katarzyna Kowol, Julia Moska, Dawid Motyka, Paweł Walkowiak, Bartosz Żuk, Arkadiusz Janz, "PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment", Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, , 2025, 23890–23919.
Anna Kołos, Katarzyna Lorenc, Emilia Wiśnios, Agnieszka Karlińska, "Behind Closed Words: Creating and Investigating the forePLay Annotated Dataset for Polish Erotic Discourse", Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, Volume 1: Long Papers, 2025, 2416–2432.