ROME: Locating and Editing Factual Associations in GPT (Paper Explained & Author Interview)

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

Paper explanation with author interview on ROME method for locating and editing factual associations in GPT models. Teaches specific technique for model manipulation.

A 65-minute video from Yannic Kilcher: “ROME: Locating and Editing Factual Associations in GPT (Paper Explained & Author Interview)”.

Video by Yannic Kilcher, played through YouTube's embedded player.

Part of Natural Language Processing, Papers Explained