Shuaiqiang Wang

Privacy (1)

large language model (19) retrieval-augmented generation (9) information retrieval (9) reinforcement learning (5) knowledge distillation (4) learning to rank (3) direct preference optimization (3) language model (3) question answering (3) transfer learning (3) benchmark dataset (2) instruction tuning (2) monte carlo tree search (2) semantic embedding (2) zero-shot learning (2) data augmentation (2) preference optimization (2) preference alignment (2) text generation (2) in-context learning (2)