Zhiyu Li

large language model (9) retrieval-augmented generation (5) reinforcement learning (3) benchmark evaluation (3) language model (2) instruction following (2) adversarial attack (2) text classification (1) information extraction (1) embedding space (1) preference learning (1) question answering (1) chain-of-thought reasoning (1) text generation (1) logical reasoning (1) domain adaptation (1) prompt learning (1) language model alignment (1) sharpness-aware minimization (1) uncertainty quantification (1)