Huashan Sun

large language model (5) catastrophic forgetting (1) zero-shot learning (1) benchmark evaluation (1) policy optimization (1) domain adaptation (1) style transfer (1) preference learning (1) in-context learning (1) chain-of-thought reasoning (1) text generation (1) text style transfer (1) evaluation framework (1) benchmark dataset (1) foundation model (1) human preference (1) large reasoning model (1) dialogue planning (1) capability evaluation (1) user simulation (1)