Lida Shi

direct preference optimization (2) contrastive learning (1) benchmark evaluation (1) text classification (1) argument mining (1) self-supervised learning (1) ancient chinese (1) language model alignment (1) semantic representation (1) machine reading comprehension (1) reinforcement learning from human feedback (1) monte carlo tree search (1) language model (1) multimodal large language model (1) dual-process theory (1) text comprehension (1) character encoding (1) historical language (1) negotiation agent (1) historical text (1)