Jinjie GU

large language model (4) causal inference (4) retrieval-augmented generation (3) continual pre-training (2) gradient descent (2) graph neural network (2) hallucination detection (2) model compression (2) recommendation system (2) knowledge distillation (2) recommender system (2) natural language generation (1) multi-task learning (1) question answering (1) in-context learning (1) knowledge editing (1) link prediction (1) empirical risk minimization (1) data subset selection (1) reinforcement learning (1)