Revising scientific papers based on peer feedback is a challenging task ...
Work on scaling laws has found that large language models (LMs) show
pre...
Selective rationales and counterfactual examples have emerged as two
eff...
Rationalization is fundamental to human reasoning and learning. NLP mode...
Making controlled perturbations is essential for various tasks (e.g., da...
Much recent work in NLP has documented dataset artifacts, bias, and spur...
Humans give contrastive explanations that explain why an observed event
...
As machine learning models are increasingly deployed in high-stakes doma...
We introduce a set of nine challenge tasks that test for the understandi...