Boshi Wang

large language model (6) in-context learning (2) sparse recovery (1) uncertainty quantification (1) natural language inference (1) bayesian optimization (1) natural language understanding (1) adversarial attack (1) out-of-distribution generalization (1) model alignment (1) belief updating (1) sparse optimization (1) text generation (1) trial and error (1) compressed sensing (1) language model (1) safety evaluation (1) systematic generalization (1) pre-trained language model (1) transformer architecture (1)