Xiaoying Zhang

large language model (6) reinforcement learning from human feedback (2) recommender system (2) reward model (2) game theory (1) uncertainty quantification (1) zero-shot learning (1) self-supervised learning (1) vision transformer (1) factual accuracy (1) explainable ai (1) task-oriented dialogue (1) language model alignment (1) dialogue state tracking (1) model alignment (1) direct preference optimization (1) instruction tuning (1) nash equilibrium (1) off-policy learning (1) knowledge extraction (1)