Francisco Navas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Francisco Navas has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Ai-Jou Chou
Wikimedia Foundation, Berlin, Germany
1 shared publication - Aitolkyn Baigutanova
Wikimedia Foundation, San Francisco, CA, USA
1 shared publication - Diego Saez-Trumper
Wikimedia Foundation, Barcelona, Spain
1 shared publication - Miriam Redi
Wikimedia Foundation, London, United Kingdom
1 shared publication - Muniza Aslam
Wikimedia Foundation, San Francisco, CA, USA
1 shared publication - Mykola Trokhymovych
Universitat Pompeu Fabra, Barcelona, Spain
1 shared publication
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8191-8199
Multilingual Reference Need Assessment System for Wikipedia
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.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8191-8199
Open AccessMultilingual Reference Need Assessment System for Wikipedia
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.