Guohua Tang

language model (2) large language model (2) direct preference optimization (1) self-supervised learning (1) knowledge distillation (1) machine translation (1) language model alignment (1) reinforcement learning from human feedback (1) model alignment (1) training efficiency (1) reward model (1) pearson correlation (1) iterative fine-tuning (1) preference datum (1) dialogue evaluation (1) language model pre-training (1) n-gram model (1) open-domain dialogue (1) data reweighting (1) soft deduplication (1)