Wikipedia may be the go-to resource on almost everything these days, but according to Meta, it’s full of useless, misquoted citations.
But don’t worry, the company says its AI is here to help, having developed Sphere, a model capable of automatically scanning hundreds of thousands of citations at once to check whether Do they really support the respective claims.
Meta claims that it created a new dataset of 134 million public web pages as the knowledge source for the model, which it says is “a magnitude larger and significantly more complex than ever before for this kind of research”. .
Circle (opens in new tab) Uses open web data instead of traditional, proprietary search engines like Google, and has already compiled 134 million documents from across the web.
built using ccnet (opens in new tab)A variant of the normal crawl, Meta says the field will help other AI researchers working on knowledge retrieval projects.
Meta says the ultimate goal of the project is to build a platform to help Wikipedia editors systematically find citation issues and quickly fix citations or mass-fix the content of related articles.
The tool reportedly draws attention to questionable citations, allowing human editors to evaluate cases that are likely to be flawed without sifting through thousands of properly cited statements.
If a citation seems irrelevant, Meta says its model will suggest a more applicable source, even pointing to the specific passage that supports the claim.
The news comes as Wikipedia is looking at new ways to raise revenue other than donations.
wikimedia enterprise (opens in new tab) The platform recently announced that it would start charging companies such as Google, Amazon and Facebook that use Wikipedia as a resource.
You can grab the source code for the project on GitHub here (opens in new tab)And interested parties can read the full article on the project’s findings here (opens in new tab) or access the demo here (opens in new tab),