Shichun Liu

large language model (6) reward model (2) reinforcement learning from human feedback (2) sequential decision making (1) preference learning (1) attention mechanism (1) in-context learning (1) question answering (1) model evaluation (1) code generation (1) task-oriented dialogue (1) question generation (1) preference modeling (1) language model (1) software testing (1) clinical evaluation (1) data contamination (1) multi-domain learning (1) human preference (1) code generation benchmark (1)