2025
PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment
Karolina Seweryn, Anna Ko{\l}os, Agnieszka Karli{\'n}ska, Katarzyna Lorenc, Katarzyna Dziewulska, Maciej Chrabaszcz +9
EMNLP 2025
Alignment is the critical process of minimizing harmful outputs by teaching large language models (LLMs) to prefer safe, helpful and appropriate responses. While the majority of alignment research and datasets remain overwhelmingly English-centric, ensuring safety across diverse linguistic and cultu