Xiangru Tang

large language model (12) benchmark evaluation (5) retrieval-augmented generation (3) factual consistency (3) prompt engineering (3) question answering (3) table-to-text generation (3) few-shot learning (3) in-context learning (2) multi-task learning (2) text classification (2) commonsense reasoning (2) dialogue summarization (2) medical reasoning (2) natural language generation (2) zero-shot learning (2) data contamination (2) claim verification (1) adversarial robustness (1) self-supervised learning (1)