Linear Alignment: A Closed-form Solution for Aligning Human Preferences Without Tuning and FeedbackSongyang Gao,Qiming Ge,Wei Shen,Shihan Dou,Junjie Ye,Xiao Wang,Rui Zheng,Yicheng Zou,Zhi Chen,Hang Yan,Qi Zhang,Dahua LinICML 2024(2024)引用 9|浏览34关键词Reinforcement Learning,Artificial IntelligencesAI 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