Year: 2025
Type: preprint
Abstract: We introduce a next-generation vandalism detection system for Wikidata, one of the largest open-source structured knowledge bases on the Web. Wikidata is highly complex: its items incorporate an ever-expanding universe of factual triples and multilingual texts. While edits can alter both structured and textual content, our approach converts all edits into a single space using a method we call Graph2Text. This allows for evaluating all content changes for potential vandalism using a single multilingual language model. This unified approach improves coverage and simplifies maintenance. Experiments demonstrate that our solution outperforms the current production system. Additionally, we are releasing the code under an open license along with a large dataset of various human-generated knowledge alterations, enabling further research.
Source: arXiv (Cornell University)
Authors: Trokhymovych, Mykola, Pintscher, Lydia, Baeza-Yates, Ricardo, Saez-Trumper, Diego
Language: English
Subfield: Communication
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W6979338590
Cites:
Cited by:
Related to: