Yulin Hu

large language model (7) safety alignment (3) preference learning (2) catastrophic forgetting (2) emotional support conversation (2) knowledge transfer (1) direct preference optimization (1) adversarial learning (1) ai safety (1) inference cost (1) instruction tuning (1) model safety (1) monte carlo tree search (1) preference modeling (1) parameter-efficient tuning (1) dialogue generation (1) supervised fine-tuning (1) jailbreak attack (1) adversarial defense (1) chain-of-thought reasoning (1)