19 citations · 25 across the 7 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.CL2021★ 2 cited
Mitigating harm in language models with conditional-likelihood filtration
Helen Ngo, Cooper Raterink, João G. M. Araújo +4
Language models trained on large-scale unfiltered datasets curated from the open web acquire systemic biases, prejudices, and harmful views from their training data. We present a m…
cs.LG2021
Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)
Sören Mindermann, Muhammed Razzak, Winnie Xu +7
We introduce Goldilocks Selection, a technique for faster model training which selects a sequence of training points that are "just right". We propose an information-theoretic acqu…