Xiaocheng Zhang

large language model (2) fact verification (1) question answering (1) preference optimization (1) prompt learning (1) reinforcement learning from human feedback (1) model alignment (1) label embedding (1) uncertainty estimation (1) bayesian neural network (1) misinformation detection (1) automatic fact-checking (1) monte carlo dropout (1) negative sample augmentation (1) retrieval system (1) neural network (1) iterative filtering (1) document-grounded dialogue (1) information interaction (1) multilingual prompt (1)