More is Less: the Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment Yifan Wang,Runjin Chen,Bolian Li, David Cho, Yihe Deng,Ruqi Zhang,Tianlong Chen, Zhangyang Wang,Ananth Grama,Junyuan Hongarxiv（2025）引用 0|浏览4AI 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
