Renren Jin

large language model (11) instruction tuning (5) benchmark evaluation (3) model compression (2) multi-task learning (1) preference learning (1) reinforcement learning (1) value alignment (1) model evaluation (1) language modeling (1) llm evaluation (1) knowledge transfer (1) low-resource language (1) generative model (1) mixture of expert (1) pairwise comparison (1) language embedding (1) supervised fine-tuning (1) direct preference optimization (1) zero-shot learning (1)