UltraFeedback: Boosting Language Models with Scaled AI Feedback

Documenti analoghi

• Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment
  di: Guo, Yiju, et al.
  Pubblicazione: (2024)
• Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models
  di: Ding, Ning, et al.
  Pubblicazione: (2024)
• Advancing LLM Reasoning Generalists with Preference Trees
  di: Yuan, Lifan, et al.
  Pubblicazione: (2024)
• The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning
  di: He, Bingxiang, et al.
  Pubblicazione: (2024)
• Noise Contrastive Alignment of Language Models with Explicit Rewards
  di: Chen, Huayu, et al.
  Pubblicazione: (2024)