Jiaru Zou

large language model (4) contextual bandit (2) link prediction (1) ensemble learning (1) sequential decision making (1) mathematical reasoning (1) in-context learning (1) benchmark dataset (1) prompt engineering (1) semantic parsing (1) document parsing (1) code generation (1) reinforcement learning from human feedback (1) multi-armed bandit (1) data augmentation (1) few-shot learning (1) reward model (1) group fairness (1) data sampling (1) zero-shot learning (1)