In tests, SIDE suggested references for featured Wikipedia articles it hadn't seen before and in nearly 50% of cases, its top choice for a reference was already cited in the article. When SIDE's results were shown to a group of Wikipedia users, 21% preferred the AI-found citations, 10% preferred the existing citations, and 39% had no preference. The tool could save time for editors and moderators checking the accuracy of Wikipedia entries if deployed correctly. However, the system's effectiveness depends on what the Wikipedia community finds most useful.
Key takeaways:
- A study suggests that artificial intelligence (AI) can help improve the quality and reliability of Wikipedia entries by cleaning up inaccurate or incomplete reference lists.
- A system called SIDE, developed by Samaya AI, uses a neural network to analyze whether Wikipedia references support the claims they’re associated with, and suggests better alternatives for those that don’t.
- In tests, SIDE was able to suggest references for featured Wikipedia articles that it had not seen before, with its top choice for a reference already cited in the article in nearly 50% of cases.
- While the tool could save time for editors and moderators checking the accuracy of Wikipedia entries, it needs to be deployed correctly and its usefulness will depend on what the Wikipedia community finds most useful.