Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models
A AraBehave is introduced: 1,623 culturally grounded, open-ended Arabic prompts with 29,214 cultural-appropriateness judgments from native speakers across several Arab regions, plus a scoring model whose predictions correlate strongly with human judgments on unseen systems.
Enes Altinisik, Hamdy Mubarak, Masoomali Fatehkia et al.
· 0 citations