Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection
This addresses vandalism detection for Wikidata, a large open-source knowledge base, though it appears incremental as it builds on existing language model approaches.
The paper tackles the problem of vandalism detection in Wikidata by converting all edits into a single space using Graph2Text, allowing evaluation with a multilingual language model. The solution outperforms the current production system, with code and a large dataset released for further research.
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.