Persistent Pre-Training Poisoning of LLMs
257 views
About this video
Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceStudies how poisoned pretraining data persists and affects downstream LLM behavior across fine-tuning. Teaches data poisoning attack mechanisms in modern language model training.
A 33-minute video from Google TechTalks: “Persistent Pre-Training Poisoning of LLMs”.
Video by Google TechTalks, played through YouTube's embedded player.
Part of Differential Privacy for ML