Ahmed Abbasi

large language model (5) fairness evaluation (3) bias mitigation (2) prompt engineering (2) model fairness (2) masked language model (2) representation learning (2) text classification (1) domain adaptation (1) contrastive learning (1) lexical semantics (1) text representation (1) pseudo labeling (1) model safety (1) few-shot learning (1) hidden state (1) user modeling (1) in-context learning (1) associative learning (1) instruction tuning (1)