Boren Zheng

large language model (3) factuality evaluation (2) chinese language (2) safety alignment (1) reinforcement learning from human feedback (1) quality control (1) retrieval-augmented generation (1) safety benchmark (1) human preference (1) preference datum (1) factuality ability (1) safety knowledge (1) harmlessness annotation (1) reinforcement learning (1) safety moderation (1) benchmark evaluation (1) question answering (1)