GPT-3 has a startling ability to produce text that sounds like it was written by a human. But a new study shows it also has a worrying proclivity for anti-Muslim bias. Researchers from Stanford and McMaster universities probed the neural network on tasks including prompt completion, analogical reasoning, and story generation. They discovered that a Muslim-violence bias appears consistently — and creatively — in various uses of the model: While these associations between Muslims and violence are learned during pretraining, they do not seem to be memorized; rather, GPT-3 manifests the underlying biases quite creatively, demonstrating the powerful ability of language models to mutate biases in different… This story continues at The Next Web

Topics:  stanford   mcmaster   muslim-violence   muslims   the next web   gpt-3   consistent   creative   study   anti-muslim bias   story   biases   ability   

 

Welcome to Wopular!

Welcome to Wopular

Wopular is an online newspaper rack, giving you a summary view of the top headlines from the top news sites.

Senh Duong (Founder)
Wopular, MWB, RottenTomatoes

Subscribe to Wopular's RSS Fan Wopular on Facebook Follow Wopular on Twitter Follow Wopular on Google Plus

MoviesWithButter : Our Sister Site

More Business News