← Search

Hannah Chen

2 accepted papers

2024

Addressing Both Statistical and Causal Gender Fairness in NLP Models

NAACL 2024findings

Statistical fairness stipulates equivalent outcomes for every protected group, whereas causal fairness prescribes that a model makes the same prediction for an individual regardless of their protected characteristics. Counterfactual data augmentation (CDA) is effective for reducing bias in NLP model…

2022

Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models

EMNLP 2022main

Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input’s true label but confuses the classifier into outputting a different prediction. Conversely, obstinate adversarial examples occur when an adversary finds a small perturbation that preserves t…