# Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection

arXiv: https://arxiv.org/abs/2505.18136 · HTML: https://mlsanity.com/paper/2505.18136/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Are All Languages Equally Hard to Language-Model?](https://mlsanity.com/paper/1806.03743/) (2018)
- [CatBoost: unbiased boosting with categorical features](https://mlsanity.com/paper/1706.09516/) (2017)
- [Building automated vandalism detection tools for Wikidata](https://mlsanity.com/paper/1703.03861/) (2017)
- [Online Disinformation and the Role of Wikipedia](https://mlsanity.com/paper/1910.12596/) (2019)
- [Fair multilingual vandalism detection system for Wikipedia](https://mlsanity.com/paper/2306.01650/) (2023)
- [Overview of the Wikidata Vandalism Detection Task at WSDM Cup 2017](https://mlsanity.com/paper/1712.05956/) (2017)
- [A Production Oriented Approach for Vandalism Detection in Wikidata - The Buffaloberry Vandalism Detector at WSDM Cup 2017](https://mlsanity.com/paper/1712.06919/) (2017)
- [Large-Scale Vandalism Detection with Linear Classifiers - The Conkerberry Vandalism Detector at WSDM Cup 2017](https://mlsanity.com/paper/1712.06920/) (2017)
- [Ensemble Models for Detecting Wikidata Vandalism with Stacking - Team Honeyberry Vandalism Detector at WSDM Cup 2017](https://mlsanity.com/paper/1712.06921/) (2017)
- [Wikidata Vandalism Detection - The Loganberry Vandalism Detector at WSDM Cup 2017](https://mlsanity.com/paper/1712.06922/) (2017)

## Built on by (most cited first, 1 of 1)

- [TERGAD: Structure-Aware Text-Enhanced Representations for Graph Anomaly Detection](https://mlsanity.com/paper/2605.19738/) (2026)

## Abstract (arXiv)

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.