Specialists Learn Faster: Knowledge Organization in Pre-training Shapes Knowledge Update Efficiency
Models pretrained on chronological knowledge update faster than shuffled generalists, and a derived law predicts that cost.
1 stories, newest first · one card per story
Models pretrained on chronological knowledge update faster than shuffled generalists, and a derived law predicts that cost.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views