mlsanityData to 14 Oct 2026

How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval

arXiv 2506.12637 ↗First posted 14 Jun 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Wikipedia is a critical resource for modern NLP, serving as a rich repository of up-to-date and citation-backed information on a wide variety of subjects. The reliability of Wikipedia -- its groundedness in its cited sources -- is vital to this purpose. This work analyzes both how grounded Wikipedia is and how readily fine-grained grounding evidence can be retrieved. To this end, we introduce PeopleProfiles -- a large-scale, multi-level dataset of claim support annotations on biographical Wikipedia articles. We show that: (1) ~22% of claims in Wikipedia lead sections are unsupported by the article body; (2) ~30% of claims in the article body are unsupported by their publicly accessible sources; and (3) real-world Wikipedia citation practices often differ from documented standards. Finally, we show that complex evidence retrieval remains a challenge -- even for recent reasoning rerankers.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 42 references that are in the map. First posted on arXiv 14 Jun 2025.

Builds on

24 of 42 references.

References · 24

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2017Billion-scale similarity search with GPUscited by 2,497
  3. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  4. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  5. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  6. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  7. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  8. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  9. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 225
  10. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 155
  11. 2023WiCE: Real-World Entailment for Claims in Wikipediacited by 120
  12. 2024Jasper and Stella: distillation of SOTA embedding modelscited by 112
12 more
  1. 2018The Fact Extraction and VERification (FEVER) Shared Taskcited by 108
  2. 2024BM25S: Orders of magnitude faster lexical search via eager sparse scoringcited by 88
  3. 2025ReasonIR: Training Retrievers for Reasoning Taskscited by 77
  4. 2025Rank1: Test-Time Compute for Reranking in Information Retrievalcited by 70
  5. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learningcited by 60
  6. 2024Molecular Facts: Desiderata for Decontextualization in LLM Fact Verificationcited by 44
  7. 2024A Closer Look at Claim Decompositioncited by 41
  8. 2025Rank-K: Test-Time Reasoning for Listwise Rerankingcited by 29
  9. 2024DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generationcited by 22
  10. 2024Language Model Probabilities are Not Calibrated in Numeric Contextscited by 18
  11. 2024Core: Robust Factual Precision with Informative Sub-Claim Identificationcited by 16
  12. 2020Natural Language Inference with Mixed Effectscited by 9

Built on by

Not cited yet.