Mingzhe Du

large language model (6) question answering (2) citation generation (2) text generation (2) code generation (2) reinforcement learning (2) data augmentation (1) machine translation (1) curriculum learning (1) named entity recognition (1) model evaluation (1) preference optimization (1) direct preference optimization (1) llm evaluation (1) hallucination mitigation (1) language model (1) domain knowledge (1) retrieval-augmented generation (1) efficiency benchmark (1) prompt engineering (1)