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

Read full text Summarise with VIRAT
Authors: Mouloud Iferroudjene, Lisa Maren Poggel, Andrea Schimmenti, Kanchan Shivashankar, Duo Yang, Jan-Christoph Kalo, Marta Boscariol
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

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.

Fields of Study & Subjects

Topic Modeling Natural Language Processing Techniques Multimodal Machine Learning Applications

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
27 March 2026
Language
FR
Document type
Dataset