# Fair multilingual vandalism detection system for Wikipedia

arXiv: https://arxiv.org/abs/2306.01650 · HTML: https://mlsanity.com/paper/2306.01650/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [CatBoost: unbiased boosting with categorical features](https://mlsanity.com/paper/1706.09516/) (2017)
- [Keeping Community in the Loop: Understanding Wikipedia Stakeholder Values for Machine Learning-Based Systems](https://mlsanity.com/paper/2001.04879/) (2020)
- [Why the World Reads Wikipedia: Beyond English Speakers](https://mlsanity.com/paper/1812.00474/) (2018)
- [Online Disinformation and the Role of Wikipedia](https://mlsanity.com/paper/1910.12596/) (2019)
- [Effects of algorithmic flagging on fairness: quasi-experimental evidence from Wikipedia](https://mlsanity.com/paper/2006.03121/) (2020)

## Built on by (most cited first, 4 of 4)

- [Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection](https://mlsanity.com/paper/2505.18136/) (2025)
- [Hoaxpedia: A Unified Wikipedia Hoax Articles Dataset](https://mlsanity.com/paper/2405.02175/) (2024)
- [Language-Agnostic Modeling of Source Reliability on Wikipedia](https://mlsanity.com/paper/2410.18803/) (2024)
- [An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation](https://mlsanity.com/paper/2604.22095/) (2026)

## Abstract (arXiv)

This paper presents a novel design of the system aimed at supporting the Wikipedia community in addressing vandalism on the platform. To achieve this, we collected a massive dataset of 47 languages, and applied advanced filtering and feature engineering techniques, including multilingual masked language modeling to build the training dataset from human-generated data. The performance of the system was evaluated through comparison with the one used in production in Wikipedia, known as ORES. Our research results in a significant increase in the number of languages covered, making Wikipedia patrolling more efficient to a wider range of communities. Furthermore, our model outperforms ORES, ensuring that the results provided are not only more accurate but also less biased against certain groups of contributors.