PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback

Documenti analoghi

• MaxMin-RLHF: Alignment with Diverse Human Preferences
  di: Chakraborty, Souradip, et al.
  Pubblicazione: (2024)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback
  di: Chakraborty, Souradip, et al.
  Pubblicazione: (2023)
• Transfer Q Star: Principled Decoding for LLM Alignment
  di: Chakraborty, Souradip, et al.
  Pubblicazione: (2024)
• SAIL: Self-Improving Efficient Online Alignment of Large Language Models
  di: Ding, Mucong, et al.
  Pubblicazione: (2024)
• Code Comprehension then Auditing for Unsupervised LLM Evaluation
  di: Patel, Bhrij, et al.
  Pubblicazione: (2024)