Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2506.12637 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908582975373312 |
|---|---|
| author | Walden, William Ricci, Kathryn Wanner, Miriam Jiang, Zhengping May, Chandler Zhou, Rongkun Van Durme, Benjamin |
| author_facet | Walden, William Ricci, Kathryn Wanner, Miriam Jiang, Zhengping May, Chandler Zhou, Rongkun Van Durme, Benjamin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12637 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval Walden, William Ricci, Kathryn Wanner, Miriam Jiang, Zhengping May, Chandler Zhou, Rongkun Van Durme, Benjamin Computation and Language 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. |
| title | How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.12637 |