conftrace_

logit pairing

3 papers

Explore in graph

Co-occurring keywords

counterfactual fairness (39) hate speech detection (723) bias mitigation (500) universal robustness (1) multi-norm perturbation (1) sensitive feature (5) counterfactual generation (59) multi-norm robustness (1) union accuracy (1) social group token (1)

Papers

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness NIPS 2024
Improving Counterfactual Generation for Fair Hate Speech Detection IJCNLP 2021
Improving Counterfactual Generation for Fair Hate Speech Detection ACL 2021