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

William Walden, Kathryn Ricci, Miriam Wanner, Zhengping Jiang, Chandler May +2 more
6/14/2025
cs.CL

No official code found. Best implementation: wgantt/people-profiles (0 stars, MIT, last commit 2025-10-09).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

MIT

Official Repository for the PeopleProfiles dataset

00May 31, 20251 years agoMIT

Similar Papers

Cite this paper

@article{walden2025grounded,
  title  = {How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval},
  author = {William Walden and Kathryn Ricci and Miriam Wanner and Zhengping Jiang and Chandler May and Rongkun Zhou and Benjamin Van Durme},
  year   = {2025},
  eprint = {2506.12637},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2506.12637v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2506.12637.svg)](https://codeofpaper.com/paper/2506.12637)

Discussion