Yizhe Yang

large language model (9) conversational agent (3) supervised fine-tuning (2) quantitative natural language inference (2) user simulation (2) reinforcement learning from human feedback (2) continual learning (2) benchmark evaluation (2) numerical reasoning (2) motivational interviewing (2) reward model (2) few-shot learning (2) dialogue system (2) speaker verification (1) text style transfer (1) domain adaptation (1) empirical study (1) text generation (1) policy optimization (1) catastrophic forgetting (1)