Lignende værker

• Revisiting Self-Play Preference Optimization: On the Role of Prompt Difficulty
  af: Xiao, Yao, et al.
  Udgivet: (2025)
• LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards
  af: Chen, Guanzheng, et al.
  Udgivet: (2026)
• LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization
  af: Chen, Guanzheng, et al.
  Udgivet: (2025)
• Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization
  af: Xiao, Yao, et al.
  Udgivet: (2025)
• CLEX: Continuous Length Extrapolation for Large Language Models
  af: Chen, Guanzheng, et al.
  Udgivet: (2023)