A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimization

Documenti analoghi

• Reward-Robust RLHF in LLMs
  di: Yan, Yuzi, et al.
  Pubblicazione: (2024)
• Policy Filtration for RLHF to Mitigate Noise in Reward Models
  di: Zhang, Chuheng, et al.
  Pubblicazione: (2024)
• Policy Optimization in RLHF: The Impact of Out-of-preference Data
  di: Li, Ziniu, et al.
  Pubblicazione: (2023)
• Factored Causal Representation Learning for Robust Reward Modeling in RLHF
  di: Yang, Yupei, et al.
  Pubblicazione: (2026)
• Learning a Pessimistic Reward Model in RLHF
  di: Xu, Yinglun, et al.
  Pubblicazione: (2025)