Large-scale vision language (VL) models use Transformers to perform
cros...
Large language models (LLMs) can perform complex reasoning in few- and
z...
Models trained via empirical risk minimization (ERM) are known to rely o...
Counterfactual data augmentation (CDA) – i.e., adding minimally perturbe...
Deep NLP models have been shown to learn spurious correlations, leaving ...
Many commonsense reasoning NLP tasks involve choosing between one or mor...
Current abstractive summarization systems outperform their extractive
co...
Natural language (NL) explanations of model predictions are gaining
popu...
Decisions of complex language understanding models can be rationalized b...
Although over 100 languages are supported by strong off-the-shelf machin...
Motivated by recent evidence pointing out the fragility of high-performi...
We present a feature vector formation technique for documents - Sparse
C...