Ananth Balashankar

Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals

2023 · arXiv (Cornell University)

Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover meaningful counterfactuals and efficiently label them, with minimal human labeling cost. …