AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
View all Papers
RefusEU dataset from "Multilingual Refusal Alignment for Safer Large Language Models" by A. Krasnodębska, W. Kusa, A. Lipani (ACL Findings 2026).
Models and datasets from "PL-Guard: Benchmarking Language Model Safety for Polish" Krasnodębska, A., Seweryn, K., Łukasik, S., & Kusa, W. (2025)
PoVisLE benchmark
RefusEU dataset from "Multilingual Refusal Alignment for Safer Large Language Models" by A. Krasnodębska, W. Kusa, A. Lipani (ACL Findings 2026).
Polish Vision-Language Model based on PLLuM and LLaVA frameworks
Models and datasets from "PL-Guard: Benchmarking Language Model Safety for Polish" Krasnodębska, A., Seweryn, K., Łukasik, S., & Kusa, W. (2025)