Jiahe Guo

large language model (5) safety alignment (3) preference learning (2) emotional support conversation (2) dialogue generation (1) model safety (1) ai safety (1) monte carlo tree search (1) preference modeling (1) adversarial defense (1) supervised fine-tuning (1) jailbreak attack (1) inference cost (1) jailbreak defense (1) strategy optimization (1) multilingual learning (1) attack success rate (1) adaptive reasoning (1) activation steering (1) role-play fine-tuning (1)