86 citations · 286 across the 17 of their papers we have counts for
4 papers · 1 filter
GeDi: Generative Discriminator Guided Sequence Generation
Ben Krause, Akhilesh Deepak Gotmare, Bryan McCann +4
While large-scale language models (LMs) are able to imitate the distribution of natural language well enough to generate realistic text, it is difficult to control which regions of…
Explaining and Improving Model Behavior with k Nearest Neighbor Representations
Nazneen Fatema Rajani, Ben Krause, Wengpeng Yin +3
Interpretability techniques in NLP have mainly focused on understanding individual predictions using attention visualization or gradient-based saliency maps over tokens. We propose…
Pointwise ergodic theorems for non-conventional bilinear polynomial averages
Ben Krause, Mariusz Mirek, Terence Tao
We establish convergence in norm and pointwise almost everywhere for the non-conventional (in the sense of Furstenberg) bilinear polynomial ergodic averages \[ A_N(f,g)(x) := \frac…
Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
Yu Bai, Ben Krause, Huan Wang +2
We propose \emph{Taylorized training} as an initiative towards better understanding neural network training at finite width. Taylorized training involves training the -th order…