4 citations · 4 across the 2 of their papers we have counts for
3 papers
cs.CL2021
Causal Distillation for Language Models
Zhengxuan Wu, Atticus Geiger, Josh Rozner +5
Distillation efforts have led to language models that are more compact and efficient without serious drops in performance. The standard approach to distillation trains a student mo…
cs.LG2021★ 4 cited
Inducing Causal Structure for Interpretable Neural Networks
Atticus Geiger, Zhengxuan Wu, Hanson Lu +5
In many areas, we have well-founded insights about causal structure that would be useful to bring into our trained models while still allowing them to learn in a data-driven fashio…
cs.AI2021
Causal Abstractions of Neural Networks
Atticus Geiger, Hanson Lu, Thomas Icard +1
Structural analysis methods (e.g., probing and feature attribution) are increasingly important tools for neural network analysis. We propose a new structural analysis method ground…