Meta explains how Your Algorithm uses LLMs to personalize Facebook recommendations
Overview
Meta says Your Algorithm lets users describe their interests in their own words and applies those preferences to recommendations in Facebook Feed and Reels.
In an engineering post, Meta says LLMs build each user's initial profile, validate edits to it, and check final recommendations against the topics a user marks as Not Interested. Meta says it is sharing how natural language preferences become recommendations and how LLMs are tailored to specific tasks within the system. The post reports no performance results.
Written by AI from the articles below · updated Nov 10, 12:56 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Engineering at MetaOfficialPickMeta explains how Your Algorithm turns stated preferences into Facebook recommendations
AIMeta says Your algorithm lets people state interests in their own words and applies those preferences to Facebook Feed and Reels. The system uses LLMs to build initial profiles, validate edits, and check final recommendations against Not Interested In topics.
Heat Trend
Not enough continuous observations to show a trend yet.