Hongyi Xin

large language model (2) lay summarization (2) transfer learning (1) direct preference optimization (1) factuality evaluation (1) text summarization (1) reward model (1) low-rank adaptation (1) retrieval-augmented generation (1) lay summary (1) instruction finetuning (1) k-shot prompting (1) section-wise summarization (1) reinforcement learning (1) readability optimization (1) reward modeling (1)