Elamur Research⌕
☰
home / papers / 2025 / WikiGap: Promoting Epistemic Equity by Surfacing Knowledge Gaps Between English Wikipedia and other Language Editions

WikiGap: Promoting Epistemic Equity by Surfacing Knowledge Gaps Between English Wikipedia and other Language Editions

Paper · 2025 · Zining Wang, Yuxuan Zhang, Dongwook Yoon et al.

Summary

English Wikipedia attracts more than eleven times the pageviews of any other edition. Many readers therefore treat it as a complete superset of all editions, but other editions hold culturally grounded facts that the English pages lack. Wikipedia's interlanguage links (ILL) let readers jump between editions, yet nothing tells them that another edition may hold extra material.

The authors built WikiGap, a browser-based extension of English Wikipedia. It pairs InfoGap, an LLM-based (GPT-4) method that finds sentence-level factual gaps across languages, with a user-centered interface. Facts missing from English but present in the French, Russian or Chinese editions appear as in-page highlights and in a sidebar, with links back to their source.

A mixed-methods study with 21 participants used fact-finding tasks on food articles. Compared with ILL navigation, WikiGap gave higher accuracy, shorter task times and a System Usability Scale score 32 points higher. Interviews showed that participants had mostly been unaware of these gaps and began to doubt English completeness. The work shows that interface design can shift reader attention toward smaller language communities.

Key points

  • English Wikipedia gets over 11× the pageviews of the next edition. A cited 2011 survey found that 93% of editors read English Wikipedia, while English was the primary language for only 52% of them.
  • The backend is InfoGap, which aligns facts between language editions using an LLM. The current scope covers English versus French, Russian and Chinese.
  • The interface follows five design elements (D1–D5): in-place access, traceability to the source edition, and multilingual engagement. It adds highlights and a sidebar without changing the normal reading layout.
  • Evaluation (n=21, food articles) compared WikiGap with the ILL baseline. WikiGap was significantly more accurate and faster, and scored +32 on SUS.
  • Stated limitations:
    • only three target languages are covered;
    • the facts shown are a random subset (a geoprovenance classifier is proposed as an improvement);
    • misinformation could spread from editions that are easier to manipulate;
    • results come from a controlled setting rather than a live deployment.

Interesting ideas

  • I1. The system compares two versions of the same article fact by fact and reports only what one version lacks, rather than merging everything into one knowledge base.
  • I2. Each surfaced fact keeps a visible link to the edition and sentence it came from, so readers can verify it.
  • I3. The evaluation uses fact-finding questions whose answers exist only in the complementary source, and it measures both accuracy and time against the current baseline.
  • I4. New material is shown as a marked overlay rather than silently rewriting the original page.
  • I5. The authors note that editions differ in how vulnerable they are to manipulation, so imported facts should be filtered by source and topic.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (world): Build worlds from two parallel texts (for example an English fable and its Ukrainian translation via the meta-world) and diff their entity/state sets to list facts that were added or lost.
  • I2 (world): Attach a source-sentence pointer and an origin tag (text, WordNet, Wikidata) to every world entity and compiled-knowledge fact, so each answer can show where each premise came from.
  • I3 (answer): Build QA probes that can be answered only through compiled knowledge, not from the tale text alone, to measure whether the knowledge layer really adds value.
  • I4 (back): When generation or translation adds inferred or imported content, mark those spans separately from content recovered from the input graph, so the compressor's fidelity can be inspected.
  • I5 (learn): Weight silver data and LLM-teacher output by the reliability of its source, and keep known-unreliable sources out of training unless several witness parsers agree.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksSocial Sciences · 1,772 worksInformation Systems · 1,437 worksCommunication · 97 worksHuman-Computer Interaction · 141 works

🧭 Topics 1Research subjects and languages the work is about.English · 2,263 works

Cite

Cite as Zining Wang, Yuxuan Zhang, Dongwook Yoon, Nicholas Vincent, Farhan Samir and Vered Shwartz. 2025. WikiGap: Promoting Epistemic Equity by Surfacing Knowledge Gaps Between English Wikipedia and other Language Editions. arXiv:2505.24195.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2505.24195 · arXiv 2505.24195

@misc{wang2025wikigap,
  title = {{WikiGap: Promoting Epistemic Equity by Surfacing Knowledge Gaps Between English Wikipedia and other Language Editions}},
  author = {Zining Wang, Yuxuan Zhang, Dongwook Yoon, Nicholas Vincent, Farhan Samir and Vered Shwartz},
  year = {2025},
  doi = {10.48550/arxiv.2505.24195},
  eprint = {2505.24195},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2505.24195}
}

References

63 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Eytan Adar, Michael Skinner, and Daniel S Weld. 2009. Information arbitrage across multi-lingual Wikipedia. In Proceedings of the Second ACM International Conference on Web Search and Data Mining. 94–103. find
  2. Leah Hope Ajmani, Jasmine C. Foriest, Jordan Taylor, Kyle Pittman, Sarah Gilbert, and Michael Ann DeVito. 2024. Whose Knowledge is Valued? Epistemic Injustice in CSCW Applications. Proc. ACM Hum.-Comput. Interact. 8, CSCW2, Article 523 (Nov. 2024), 28 pages. doi:10.1145/3687062 ↗
  3. Ofer Arazy, Hila Liifshitz-Assaf, Oded Nov, Johannes Daxenberger, Martina Balestra, and Coye Cheshire. 2017. On the "How" and "Why" of Emergent Role Behaviors in Wikipedia. In Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing (Portland, Oregon, USA) (CSCW ’17). Association for Computing Machinery, New York, NY, USA, 2039–2051. doi:10.1145/2998181.2998317 ↗
  4. Bunty Avieson and Suruchi Mazumdar. 2025. Wiki warriors: language editors counter knowledge hierarchies during the pandemic. Asian Journal of Communication (2025), 1–19. ↗
  5. Aaron Bangor, Philip Kortum, and James Miller. 2009. Determining what individual SUS scores mean: adding an adjective rating scale. J. Usability Studies 4, 3 (May 2009), 114–123. find
  6. Patti Bao, Brent Hecht, Samuel Carton, Mahmood Quaderi, Michael Horn, and Darren Gergle. 2012. Omnipedia: bridging the wikipedia language gap. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 1075–1084. find
  7. Shaowen Bardzell. 2010. Feminist HCI: taking stock and outlining an agenda for design. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (Atlanta, Georgia, USA) (CHI ’10). Association for Computing Machinery, New York, NY, USA, 1301–1310. doi:10.1145/1753326. 1753521 ↗
  8. Ruha Benjamin. 2023. Race after technology. In Social Theory Re-Wired. Routledge, 405–415. ↗
  9. Ewa S Callahan and Susan C Herring. 2011. Cultural bias in Wikipedia content on famous persons. Journal of the American society for information science and technology 62, 10 (2011), 1899–1915. ↗
  10. Shruthi Chockkalingam, Seyed Hossein Alavi, Raymond T. Ng, and Vered Shwartz. 2025. Should I go vegan: Evaluating the Persuasiveness of LLMs in Persona-Grounded Dialogues. In Proceedings of the Third Workshop on Social Influence in Conversations (SICon 2025), James Hale, Brian Deuksin Kwon, and Ritam Dutt (Eds.). Association for Computational Linguistics, Vienna, Austria, 65–72. doi:10.18653/v1/2025.sicon-1.4 ↗
  11. Noam Cohen. 2008. Open-Source Troubles in Wiki World. New York Times. https://www.nytimes.com/2008/03/17/technology/17wikipedia.html ↗
  12. Wei Dong and Wai-Tat Fu. 2010. Cultural difference in image tagging. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (Atlanta, Georgia, USA) (CHI ’10). Association for Computing Machinery, New York, NY, USA, 981–984. doi:10.1145/1753326.1753472 ↗
  13. Amir Dotan and Panayiotis Zaphiris. 2010. A cross-cultural analysis of Flickr users from Peru, Israel, Iran, Taiwan and the UK. Int. J. Web Based Communities 6, 3 (June 2010), 284–302. doi:10.1504/IJWBC.2010.033753 ↗
  14. Kevin Duh, Ching-Man Au Yeung, Tomoharu Iwata, and Masaaki Nagata. 2013. Managing information disparity in multilingual document collections. ACM Transactions on Speech and Language Processing (TSLP) 10, 1 (2013), 1–28. ↗
  15. Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, and Wei Wang. 2020. Language-agnostic BERT Sentence Embedding. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, 879–894. https://arxiv.org/abs/2007.01852 ↗
  16. Michel Foucault. 2013. Archaeology of knowledge. routledge. find
  17. Omer Goldman, Uri Shaham, Dan Malkin, Sivan Eiger, Avinatan Hassidim, Yossi Matias, Joshua Maynez, Adi Mayrav Gilady, Jason Riesa, Shruti Rijhwani, Laura Rimell, Idan Szpektor, Reut Tsarfaty, and Matan Eyal. 2025. ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfer. arXiv:2502.21228 [cs.CL] https://arxiv.org/abs/2502.21228 ↗
  18. David Golumbia. 2009. The cultural logic of computation. Harvard University Press. ↗
  19. Mark Graham, Scott A. Hale, and Devin Gaffney. 2014. Where in the World Are You? Geolocation and Language Identification in Twitter. The Professional Geographer 66, 4 (2014), 568–578. doi:10.1080/00330124.2014.907699 arXiv:https://doi.org/10.1080/00330124.2014.907699 ↗
  20. Jonathan Grudin. 1988. Why CSCW applications fail: problems in the design and evaluationof organizational interfaces. In Proceedings of the 1988 ACM Conference on Computer-Supported Cooperative Work (Portland, Oregon, USA) (CSCW ’88). Association for Computing Machinery, New York, NY, USA, 85–93. doi:10.1145/62266.62273 ↗
  21. Scott A Hale. 2014. Multilinguals and Wikipedia editing. In Proceedings of the 2014 ACM conference on Web science. 99–108. find
  22. Donna Haraway. 2013. Situated knowledges: The science question in feminism and the privilege of partial perspective 1. In Women, science, and technology. Routledge, 455–472. Manuscript submitted to ACM find
  23. Jean Hardy and Jacob Thebault-Spieker. 2024. A Turn to Assets in Community-Based Computing Research: Tradeoffs, Deficits, and Neoliberalism in Technological Development. Proc. ACM Hum.-Comput. Interact. 8, CSCW1, Article 14 (April 2024), 20 pages. doi:10.1145/3637291 ↗
  24. Brent Hecht and Darren Gergle. 2009. Measuring self-focus bias in community-maintained knowledge repositories. In Proceedings of the fourth international conference on communities and technologies. 11–20. find
  25. Brent Hecht and Darren Gergle. 2010. The tower of Babel meets web 2.0: user-generated content and its applications in a multilingual context. In Proceedings of the SIGCHI conference on human factors in computing systems. 291–300. find
  26. Brent Jaron Hecht. 2013. The mining and application of diverse cultural perspectives in user-generated content. Ph. D. Dissertation. Northwestern University. find
  27. Daniel Hershcovich, Stella Frank, Heather Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, Constanza Fierro, Katerina Margatina, Phillip Rust, and Anders Søgaard. 2022. Challenges and Strategies in Cross-Cultural NLP. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Smaranda Muresan, Preslav Nakov, and Aline Villavicencio (Eds.). Association for Computational Linguistics, Dublin, Ireland, 6997–7013. doi:10.18653/v1/2022.acl-long.482 ↗
  28. Molly G Hickman, Viral Pasad, Harsh Kamalesh Sanghavi, Jacob Thebault-Spieker, and Sang Won Lee. 2021. Understanding wikipedia practices through hindi, urdu, and english takes on an evolving regional conflict. Proceedings of the ACM on Human-Computer Interaction 5, CSCW1 (2021), 1–31. ↗
  29. Cheryl I Johnson and Richard E Mayer. 2012. An eye movement analysis of the spatial contiguity effect in multimedia learning. Journal of Experimental Psychology: Applied 18, 2 (2012), 178. ↗
  30. Isaac Johnson and Emily Lescak. 2022. Considerations for multilingual wikipedia research. arXiv preprint arXiv:2204.02483 (2022). ↗
  31. Zarine Kharazian, Kate Starbird, and Benjamin Mako Hill. 2024. Governance capture in a self-governing community: A qualitative comparison of the croatian, serbian, bosnian, and serbo-croatian wikipedias. Proceedings of the ACM on Human-Computer Interaction 8, CSCW1 (2024), 1–26. ↗
  32. Sejal Khatri, Aaron Shaw, Sayamindu Dasgupta, and Benjamin Mako Hill. 2022. The social embeddedness of peer production: A comparative qualitative analysis of three Indian language Wikipedia editions. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems. 1–18. find
  33. John P. Kretzman and John McKnight. 1993. Building Communities from the Inside Out: A Path Toward Finding and Mobilizing a Community’s Assets. https://api.semanticscholar.org/CorpusID:109453662 ↗
  34. Sangeet Kumar. 2021. The digital frontier: Infrastructures of control on the global web. Indiana University Press. find
  35. Paul Laufer, Claudia Wagner, Fabian Flöck, and Markus Strohmaier. 2015. Mining cross-cultural relations from Wikipedia: a study of 31 European food cultures. In Proceedings of the ACM web science conference. 1–10. ↗
  36. Yiwei Luo, Kristina Gligoric, and Dan Jurafsky. 2023. Othering and Low Status Framing of Immigrant Cuisines in US Restaurant Reviews and Large Language Models. In International Conference on Web and Social Media. https://api.semanticscholar.org/CorpusID:259936860 ↗
  37. Emanuel Maiberg. 2025. Wikipedia Says AI Is Causing a Dangerous Decline in Human Visitors. 404 Media (2025). https://www.404media.co/wikipedia-says-ai-is-causing-a-dangerous-decline-in-human-visitors/ Published online 16 October 2025; accessed 2025-12-03. ↗
  38. Catherine C Marshall. 1997. Annotation: from paper books to the digital library. In Proceedings of the second ACM international conference on Digital libraries. 131–140. find
  39. Paolo Massa and Federico Scrinzi. 2012. Manypedia: Comparing language points of view of Wikipedia communities. In Proceedings of the Eighth Annual International Symposium on Wikis and Open Collaboration. 1–9. ↗
  40. Julia Mendelsohn, Sayan Ghosh, David Jurgens, and Ceren Budak. 2023. Bridging nations: quantifying the role of multilinguals in communication on social media. In Proceedings of the International AAAI Conference on Web and Social Media, Vol. 17. 626–637. find
  41. Rada Mihalcea, Oana Ignat, Longju Bai, Angana Borah, Luis Chiruzzo, Zhijing Jin, Claude Kwizera, Joan Nwatu, Soujanya Poria, and Thamar Solorio. 2025. Why AI Is WEIRD and Shouldn’t Be This Way: Towards AI for Everyone, with Everyone, by Everyone. Proceedings of the AAAI Conference on Artificial Intelligence 39, 27 (Apr. 2025), 28657–28670. doi:10.1609/aaai.v39i27.35092 ↗
  42. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Wei Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. Factscore: Fine-grained atomic evaluation of factual precision in long form text generation. arXiv preprint arXiv:2305.14251 (2023). ↗
  43. Marc Miquel-Ribé and David Laniado. 2018. Wikipedia culture gap: quantifying content imbalances across 40 language editions. Frontiers in physics 6 (2018), 54. ↗
  44. Marc Miquel-Ribé and David Laniado. 2020. The Wikipedia Diversity Observatory: A Project to Identify and Bridge Content Gaps in Wikipedia. In Proceedings of the 16th International Symposium on Open Collaboration (Virtual conference, Spain) (OpenSym ’20). Association for Computing Machinery, New York, NY, USA, Article 14, 4 pages. doi:10.1145/3412569.3412866 ↗
  45. Hellina Hailu Nigatu, John Canny, and Sarah E Chasins. 2024. Low-Resourced Languages and Online Knowledge Repositories: A Need-Finding Study.. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–21. find
  46. Oded Nov. 2007. What motivates Wikipedians? Commun. ACM 50, 11 (Nov. 2007), 60–64. doi:10.1145/1297797.1297798 ↗
  47. OpenAI. 2024. GPT-4o mini: Advancing Cost-Efficient Intelligence. https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence. Large language model, July 18 version. ↗
  48. OpenAI. 2024. GPT-4o System Card. arXiv preprint arXiv:2410.21276 (2024). https://arxiv.org/abs/2410.21276 ↗
  49. Peter Pirolli and Stuart Card. 1999. Information foraging. Psychological review 106, 4 (1999), 643. Manuscript submitted to ACM find
  50. Dwaipayan Roy, Sumit Bhatia, and Prateek Jain. 2022. Information asymmetry in Wikipedia across different languages: A statistical analysis. Journal of the Association for Information Science and Technology 73, 3 (2022), 347–361. ↗
  51. Edward W Said. 1977. Orientalism. The Georgia Review 31, 1 (1977), 162–206. find
  52. Farhan Samir, Chan Young Park, Anjalie Field, Vered Shwartz, and Yulia Tsvetkov. 2024. Locating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on Wikipedia. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (Eds.). Association for Computational Linguistics, Miami, Florida, USA, 6747–6762. doi:10.18653/v1/2024.emnlp-main.384 ↗
  53. Kjeld Schmidt and Liam Bannon. 1992. Taking CSCW seriously. 1, 1 (1992), 7–40. doi:10.1007/BF00752449 ↗
  54. Shilad W Sen, Heather Ford, David R Musicant, Mark Graham, OS Keyes, and Brent Hecht. 2015. Barriers to the localness of volunteered geographic information. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. 197–206. find
  55. Chirag Shah and Emily M Bender. 2022. Situating search. In Proceedings of the 2022 Conference on Human Information Interaction and Retrieval. 221–232. find
  56. Susan Leigh Star. 2010. This is Not a Boundary Object: Reflections on the Origin of a Concept. Science, Technology, & Human Values 35, 5 (2010), 601–617. doi:10.1177/0162243910377624 arXiv:https://doi.org/10.1177/0162243910377624 ↗
  57. Susan Leigh Star and James R. Griesemer. 1989. Institutional Ecology, ‘Translations’ and Boundary Objects: Amateurs and Professionals in Berkeley’s Museum of Vertebrate Zoology, 1907-39. Social Studies of Science 19, 3 (1989), 387–420. doi:10.1177/030631289019003001 arXiv:https://doi.org/10.1177/030631289019003001 ↗
  58. Yan Tao, Olga Viberg, Ryan S Baker, and René F Kizilcec. 2024. Cultural bias and cultural alignment of large language models. PNAS nexus 3, 9 (2024), pgae346. ↗
  59. Nicholas Vincent and Brent Hecht. 2021. A deeper investigation of the importance of Wikipedia links to search engine results. Proceedings of the ACM on Human-Computer Interaction 5, CSCW1 (2021), 1–15. ↗
  60. Wikimedia Foundation. 2011. Editor Survey Report – April 2011. Technical Report. Wikimedia Foundation. https://upload.wikimedia.org/wikipedia/commons/7/76/Editor_Survey_Report_-_April_2011.pdf Accessed. ↗
  61. Wikimedia Foundation. 2024. Announcing English Wikipedia’s most popular articles of 2024. https://wikimediafoundation.org/news/2024/12/03/announcing-english-wikipedias-most-popular-articles-of-2024/ Accessed: 2025-09-09. ↗
  62. Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan, David Anugraha, Rifki Afina Putri, Wang Yutong, Adam Nohejl, Ubaidillah Ariq Prathama, Nedjma Ousidhoum, Afifa Amriani, Anar Rzayev, Anirban Das, Ashmari Pramodya, Aulia Adila, Bryan Wilie, Candy Olivia Mawalim, Cheng Ching Lam, Daud Abolade, Emmanuele Chersoni, Enrico Santus, Fariz Ikhwantri, Garry Kuwanto, Hanyang Zhao, Haryo Akbarianto Wibowo, Holy Lovenia, Jan Christian Blaise Cruz, Jan Wira Gotama Putra, Junho Myung, Lucky Susanto, Maria Angelica Riera Machin, Marina Zhukova, Michael Anugraha, Muhammad Farid Adilazuarda, Natasha Christabelle Santosa, Peerat Limkonchotiwat, Raj Dabre, Rio Alexander Audino, Samuel Cahyawijaya, Shi-Xiong Zhang, Stephanie Yulia Salim, Yi Zhou, Yinxuan Gui, David Ifeoluwa Adelani, En-Shiun Annie Lee, Shogo Okada, Ayu Purwarianti, Alham Fikri Aji, Taro Watanabe, Derry Tanti Wijaya, Alice Oh, and Chong-Wah Ngo. 2025. WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Luis Chiruzzo, Alan Ritter, and Lu Wang (Eds.). Association for Computational Linguistics, Albuquerque, New Mexico, 3242–3264. https://aclanthology.org/2025.naacl-long.167/ ↗
  63. Marisol Wong-Villacres, Aakash Gautam, Wendy Roldan, Lucy Pei, Jessa Dickinson, Azra Ismail, Betsy DiSalvo, Neha Kumar, Tammy Clegg, Sheena Erete, Emily Roden, Nithya Sambasivan, and Jason Yip. 2020. From Needs to Strengths: Operationalizing an Assets-Based Design of Technology. In Companion Publication of the 2020 Conference on Computer Supported Cooperative Work and Social Computing (Virtual Event, USA) (CSCW ’20 Companion). Association for Computing Machinery, New York, NY, USA, 527–535. doi:10.1145/3406865.3418594 ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2025-wikigap-promoting-epistemic-equity-surfacing/