Huangyu Dai

large language model (3) multi-task learning (1) preference learning (1) neural machine translation (1) information retrieval (1) instruction following (1) information entropy (1) information gain (1) low-rank adaptation (1) parameter efficient fine-tuning (1) universal learning (1) mixture of expert (1) hallucination mitigation (1) prompt optimization (1) retrieval-augmented generation (1) implicit reasoning (1) answer generation (1) token generation (1) token-level learning (1) domain-specific learning (1)