Transformer-based language models (LMs) are known to capture factual
kno...
In this work, we explore whether modeling recurrence into the Transforme...
Recent neural network-based language models have benefited greatly from
...
When explaining AI behavior to humans, how is the communicated informati...
Feature attribution a.k.a. input salience methods which assign an import...
We introduce Autoregressive Diffusion Models (ARDMs), a model class
enco...
Experiments with pretrained models such as BERT are often based on a sin...
There is a recent surge of interest in using attention as explanation of...
We present the Language Interpretability Tool (LIT), an open-source plat...