Xiaohui Hu

causal inference (1) few-shot learning (1) object detection (1) direct preference optimization (1) knowledge distillation (1) factual accuracy (1) neural machine translation (1) syntactic parsing (1) masked language model (1) reinforcement learning from human feedback (1) model alignment (1) sequential dependency (1) preference modeling (1) reward model (1) supervised fine-tuning (1) hallucination mitigation (1) structural causal model (1) causal explanation (1) graph convolutional network (1) backdoor adjustment (1)