Ed Chi

large language model (3) adversarial learning (2) counterfactual data augmentation (2) model robustness (2) multi-task learning (2) spurious correlation (2) transfer learning (2) domain generalization (1) collaborative filtering (1) policy optimization (1) policy gradient (1) text classification (1) knowledge distillation (1) prompt engineering (1) few-shot learning (1) feature embedding (1) toxicity detection (1) sentiment classification (1) adversarial training (1) chain-of-thought reasoning (1)