Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL

Ähnliche Einträge

• The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration
  von: Yao, Wei, et al.
  Veröffentlicht: (2025)
• Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning
  von: Zhang, Yixian, et al.
  Veröffentlicht: (2025)
• On Weak-to-Strong Generalization and f-Divergence
  von: Yao, Wei, et al.
  Veröffentlicht: (2025)
• Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint
  von: Xiong, Wei, et al.
  Veröffentlicht: (2023)
• Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
  von: Yang, Wenkai, et al.
  Veröffentlicht: (2024)