類似資料

• KTO: Model Alignment as Prospect Theoretic Optimization
  著者:: Ethayarajh, Kawin, 等
  出版事項: (2024)
• Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
  著者:: D'Oosterlinck, Karel, 等
  出版事項: (2024)
• MathScale: Scaling Instruction Tuning for Mathematical Reasoning
  著者:: Tang, Zhengyang, 等
  出版事項: (2024)
• OLMoE: Open Mixture-of-Experts Language Models
  著者:: Muennighoff, Niklas, 等
  出版事項: (2024)
• Great Models Think Alike and this Undermines AI Oversight
  著者:: Goel, Shashwat, 等
  出版事項: (2025)