However, there's a lack of insight into how these models perform in terms

The word embedding space in neural models is skewed, and correcting this can improve task performance.

Sign languages are the primary form of communication for millions of deaf individuals.

Concept erasure aims to remove specified features from a representation. It can improve fairness (e.g.

Training data attribution (TDA) techniques find influential training data for the model's prediction on the test data of interest.