類似資料

• Improve Mathematical Reasoning in Language Models by Automated Process Supervision
  著者:: Luo, Liangchen, 等
  出版事項: (2024)
• RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
  著者:: Lee, Harrison, 等
  出版事項: (2023)
• Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
  著者:: Xiao, Teng, 等
  出版事項: (2024)
• Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing
  著者:: Qi, Biqing, 等
  出版事項: (2024)
• MixDPO: Modeling Preference Strength for Pluralistic Alignment
  著者:: Imai, Saki, 等
  出版事項: (2026)