Chengguang Tang

knowledge distillation (2) large language model (2) reward modeling (1) few-shot learning (1) preference learning (1) direct preference optimization (1) self-supervised learning (1) machine translation (1) language model alignment (1) natural language understanding (1) low-resource learning (1) reinforcement learning from human feedback (1) model alignment (1) knowledge graph (1) language model (1) reward model (1) pearson correlation (1) pre-trained model (1) iterative fine-tuning (1) pre-trained language model (1)