用语言模型统一检测维基数据的恶意编辑，提升准确率与维护效率。
Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection
- 将结构化和文本编辑统一转为文本，用单个多语言模型评估
- 实验显示优于现有生产系统，覆盖更全面
- 开源代码与大规模数据集，适合知识库安全研究者
我们提出一种新一代维基数据恶意编辑检测系统，该系统针对全球最大的开源结构化知识库之一——维基数据。维基数据内容复杂，包含不断扩展的事实三元组与多语言文本。编辑可同时影响结构化数据与文本内容。本文提出Graph2Text方法，将所有编辑转换到统一文本空间，从而使用单一多语言语言模型评估潜在恶意行为。该统一方法提升了检测覆盖率并简化了系统维护。实验表明，该方案优于当前生产系统。此外，我们已开源代码及一个大规模人工生成的知识变更数据集，支持后续研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。