類似資料

• GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
  著者:: Tan, Hongze, 等
  出版事項: (2025)
• T-REG: Preference Optimization with Token-Level Reward Regularization
  著者:: Zhou, Wenxuan, 等
  出版事項: (2024)
• Selective Preference Optimization via Token-Level Reward Function Estimation
  著者:: Yang, Kailai, 等
  出版事項: (2024)
• Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
  著者:: Zhou, Jiayi, 等
  出版事項: (2024)
• Reward Modeling with Ordinal Feedback: Wisdom of the Crowd
  著者:: Liu, Shang, 等
  出版事項: (2024)