Huiyuan Zheng

large language model (3) transfer learning (1) domain adaptation (1) attention mechanism (1) preference alignment (1) task-oriented dialogue (1) question generation (1) ai safety (1) reinforcement learning from human feedback (1) model alignment (1) preference modeling (1) reward model (1) multi-domain learning (1) human preference (1) slot filling (1) human alignment (1) constitutional ai (1) open named entity recognition (1) reinforcement learning (1) universal entity taxonomy (1)