WILA-PopQA: Popularity-matched Multilingual Wikidata dataset for Question Answering

WILA-PopQA is a popularity-matched multilingual Wikidata question answering dataset designed to evaluate factual QA across languages under controlled conditions. It disentangles the language of the question from the language associated with the entity, enabling the study of cross-lingual bias in multilingual language models. The dataset contains Wikidata-grounded questions about notable deceased persons across several biographical properties, with entity selection constrained by multilingual completeness and popularity balancing based on Wikipedia sitelinks.