Research

Paper

TESTING March 17, 2026

Multilingual Reference Need Assessment System for Wikipedia

Authors

Aitolkyn Baigutanova, Francisco Navas, Pablo Aragon, Mykola Trokhymovych, Muniza Aslam, Ai-Jou Chou, Miriam Redi, Diego Saez-Trumper

Abstract

Wikipedia is a critical source of information for millions of users across the Web. It serves as a key resource for large language models, search engines, question-answering systems, and other Web-based applications. In Wikipedia, content needs to be verifiable, meaning that readers can check that claims are backed by references to reliable sources. This depends on manual verification by editors, an effective but labor-intensive process, especially given the high volume of daily edits. To address this challenge, we introduce a multilingual machine learning system to assist editors in identifying claims requiring citations. Our approach is tested in 10 language editions of Wikipedia, outperforming existing benchmarks for reference need assessment. We not only consider machine learning evaluation metrics but also system requirements, allowing us to explore the trade-offs between model accuracy and computational efficiency under real-world infrastructure constraints. We deploy our system in production and release data and code to support further research.

Metadata

arXiv ID: 2603.17146
Provider: ARXIV
Primary Category: cs.CY
Published: 2026-03-17
Fetched: 2026-03-19 06:01

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.17146v1</id>\n    <title>Multilingual Reference Need Assessment System for Wikipedia</title>\n    <updated>2026-03-17T21:20:40Z</updated>\n    <link href='https://arxiv.org/abs/2603.17146v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.17146v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Wikipedia is a critical source of information for millions of users across the Web. It serves as a key resource for large language models, search engines, question-answering systems, and other Web-based applications. In Wikipedia, content needs to be verifiable, meaning that readers can check that claims are backed by references to reliable sources. This depends on manual verification by editors, an effective but labor-intensive process, especially given the high volume of daily edits. To address this challenge, we introduce a multilingual machine learning system to assist editors in identifying claims requiring citations. Our approach is tested in 10 language editions of Wikipedia, outperforming existing benchmarks for reference need assessment. We not only consider machine learning evaluation metrics but also system requirements, allowing us to explore the trade-offs between model accuracy and computational efficiency under real-world infrastructure constraints. We deploy our system in production and release data and code to support further research.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CY'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-17T21:20:40Z</published>\n    <arxiv:comment>Accepted for publication at the Proceedings of the ACM Web Conference 2026 (WWW '26). Author's copy</arxiv:comment>\n    <arxiv:primary_category term='cs.CY'/>\n    <arxiv:journal_ref>Proceedings of the ACM Web Conference 2026 (WWW '26), April 13--17, 2026, Dubai, United Arab Emirates</arxiv:journal_ref>\n    <author>\n      <name>Aitolkyn Baigutanova</name>\n    </author>\n    <author>\n      <name>Francisco Navas</name>\n    </author>\n    <author>\n      <name>Pablo Aragon</name>\n    </author>\n    <author>\n      <name>Mykola Trokhymovych</name>\n    </author>\n    <author>\n      <name>Muniza Aslam</name>\n    </author>\n    <author>\n      <name>Ai-Jou Chou</name>\n    </author>\n    <author>\n      <name>Miriam Redi</name>\n    </author>\n    <author>\n      <name>Diego Saez-Trumper</name>\n    </author>\n    <arxiv:doi>10.1145/3774904.3792803</arxiv:doi>\n    <link href='https://doi.org/10.1145/3774904.3792803' rel='related' title='doi'/>\n  </entry>"
}