mlsanityData to 7 Oct 2026

Improving Wikipedia Verifiability with AI

arXiv 2207.06220 ↗First posted 8 Jul 2022cs.IR cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Verifiability is a core content policy of Wikipedia: claims that are likely to be challenged need to be backed by citations. There are millions of articles available online and thousands of new articles are released each month. For this reason, finding relevant sources is a difficult task: many claims do not have any references that support them. Furthermore, even existing citations might not support a given claim or become obsolete once the original source is updated or deleted. Hence, maintaining and improving the quality of Wikipedia references is an important challenge and there is a pressing need for better tools to assist humans in this effort. Here, we show that the process of improving references can be tackled with the help of artificial intelligence (AI). We develop a neural network based system, called Side, to identify Wikipedia citations that are unlikely to support their claims, and subsequently recommend better ones from the web. We train this model on existing Wikipedia references, therefore learning from the contributions and combined wisdom of thousands of Wikipedia editors. Using crowd-sourcing, we observe that for the top 10% most likely citations to be tagged as unverifiable by our system, humans prefer our system's suggested alternatives compared to the originally cited reference 70% of the time. To validate the applicability of our system, we built a demo to engage with the English-speaking Wikipedia community and find that Side's first citation recommendation collects over 60% more preferences than existing Wikipedia citations for the same top 10% most likely unverifiable claims according to Side. Our results indicate that an AI-based system could be used, in tandem with humans, to improve the verifiability of Wikipedia. More generally, we hope that our work can be used to assist fact checking efforts and increase the general trustworthiness of information online.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 32 of its 57 references that are in the map. First posted on arXiv 8 Jul 2022.

Builds on

32 of 57 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  6. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  7. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 798
  8. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  9. 2019CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Datacited by 544
  10. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  11. 2018Generating Wikipedia by Summarizing Long Sequencescited by 333
  12. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 222
20 more
  1. 2020Sparse, Dense, and Attentional Representations for Text Retrievalcited by 213
  2. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  3. 2017Automatic Detection of Fake Newscited by 145
  4. 2018Automated Fact Checking: Task formulations, methods and future directionscited by 96
  5. 2019Scalable Zero-shot Entity Linking with Dense Entity Retrievalcited by 85
  6. 2019Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Indexcited by 64
  7. 2021Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representationscited by 60
  8. 2021The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpuscited by 60
  9. 2021Domain-matched Pre-training Tasks for Dense Retrievalcited by 53
  10. 2021Multi-task Retrieval for Knowledge-Intensive Taskscited by 44
  11. 2018Content-Based Citation Recommendationcited by 43
  12. 2020Citation Recommendation: Approaches and Datasetscited by 36
  13. 2019Citation Needed: A Taxonomy and Algorithmic Assessment of Wikipedia's Verifiabilitycited by 16
  14. 2019Towards Content Transfer through Grounded Text Generationcited by 9
  15. 2021On the Value of Wikipedia as a Gateway to the Webcited by 6
  16. 2020Quantifying Engagement with Citations on Wikipediacited by 4
  17. 2017Fine Grained Citation Span for References in Wikipediacited by 2
  18. 2018WikiRef: Wikilinks as a route to recommending appropriate references for scientific Wikipedia pagescited by 1
  19. 2020'I Updated the <ref>': The Evolution of References in the English Wikipedia and the Implications for Altmetricscited by 1
  20. 2021References in Wikipedia: The Editors' Perspectivecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 3; 2025: 0; 2026: 3.

11 papers.

  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  2. 2023RewriteLM: An Instruction-Tuned Large Language Model for Text Rewritingcited by 67
  3. 2023RELIC: Investigating Large Language Model Responses using Self-Consistencycited by 23
  4. 2024kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabulariescited by 20
  5. 2024Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decompositioncited by 12
  6. 2023MegaWika: Millions of reports and their sources across 50 diverse languagescited by 9
  7. 2023LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interactioncited by 7
  8. 2026Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attributioncited by 2
  9. 2024A Content-Based Novelty Measure for Scholarly Publications: A Proof of Conceptcited by 1
  10. 2026Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learningcited by 0
  11. 2026A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memorycited by 0