LLM Dataset Inference: Did you train on my dataset?

About this video

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Presents methods for inferring whether specific datasets were used in LLM training. Teaches techniques for reverse-engineering training data composition.

A 44-minute video from Google TechTalks: “LLM Dataset Inference: Did you train on my dataset?”.

Video by Google TechTalks, played through YouTube's embedded player.

Part of Differential Privacy for ML