Kexin Huang

large language model (6) graph neural network (5) safety evaluation (2) few-shot learning (1) uncertainty quantification (1) graph representation learning (1) feature extraction (1) token selection (1) information retrieval (1) toxicity detection (1) text representation (1) bias detection (1) privacy preservation (1) geometric deep learning (1) out-of-distribution generalization (1) knowledge unlearning (1) ai safety (1) knowledge base (1) safety alignment (1) question answering (1)