Yongjie Wang

model interpretability (2) text classification (2) adversarial learning (1) concept-based explanation (1) transfer learning (1) natural language processing (1) deep learning (1) out-of-distribution generalization (1) bert language model (1) pre-trained model (1) spurious correlation (1) multi-scale representation (1) automated essay scoring (1) counterfactual augmentation (1) counterfactual generation (1) model fairness (1) large language model (1) high-impact concept (1) predictive impact (1) causal inference (1)