Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916755178258432 |
|---|---|
| author | Trokhymovych, Mykola Pintscher, Lydia Baeza-Yates, Ricardo Saez-Trumper, Diego |
| author_facet | Trokhymovych, Mykola Pintscher, Lydia Baeza-Yates, Ricardo Saez-Trumper, Diego |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18136 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection Trokhymovych, Mykola Pintscher, Lydia Baeza-Yates, Ricardo Saez-Trumper, Diego Computation and Language Artificial Intelligence 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. |
| title | Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.18136 |