Xudong Han

large language model (7) bias mitigation (6) debiasing method (4) text classification (2) group bia (2) risk assessment (2) predictive fairness (2) harmful content detection (2) model debiasing (2) equal opportunity (2) modifier dynamics (2) bias detection (2) adversarial training (2) class imbalance (2) model training (2) fairness evaluation (2) model safety (1) binary classification (1) model evaluation (1) model security (1)