Erxue Min

large language model (3) direct preference optimization (3) contrastive learning (1) sample efficiency (1) self-attention mechanism (1) mathematical reasoning (1) preference alignment (1) social network (1) data augmentation (1) in-context learning (1) information retrieval (1) preference optimization (1) conversational search (1) matrix approximation (1) hierarchical decomposition (1) reinforcement learning (1) information gain (1) parameter-efficient fine-tuning (1) low-rank adaptation (1) transformer architecture (1)