VentureBeat January 3, 2025
Ben Dickson

Meta — parent company of Facebook, Instagram, WhatsApp, Threads and more — runs one of the biggest recommendation systems in the world.

In two recently released papers, its researchers have revealed how generative models can be used to better understand and respond to user intent.

By looking at recommendations as a generative problem, you can tackle it in new ways that are richer in content and more efficient than classic approaches. This approach can have important uses for any application that requires retrieving documents, products or other kinds of objects.

Dense vs generative retrieval

The standard approach to creating recommendation systems is to compute, store and retrieve dense representations of documents. For example, to recommend items to users, an...

Today's Sponsors

Venturous
Got healthcare questions? Just ask Transcarent

Today's Sponsor

Venturous

 
Topics: AI (Artificial Intelligence), Technology
A novel idea for controlling chatbots
HIMSS25 Keeps the Party Going. Can Everyone Keep Up?
Debunked Episode 13: Will the Real AI Please Stand Up?
Why 35 health systems teamed up on AI
A Bright Future for AI in Pharma

Share This Article