Keeping LLMs Aligned after Fine-tuning: the Crucial Role of Prompt TemplatesKaifeng Lyu,Haoyu Zhao,Xinran Gu,Dingli Yu,Anirudh Goyal,Sanjeev AroraNeurIPS 2024(2024)引用 37|浏览46关键词safety prompt,AI alignmentAI 理解论文溯源树样例生成溯源树,研究论文发展脉络Chat Paper正在生成论文摘要