Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

Documenti analoghi

• Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
  di: Shen, Wei, et al.
  Pubblicazione: (2024)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization
  di: Ji, Kaixuan, et al.
  Pubblicazione: (2024)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
  di: Hong, Ilgee, et al.
  Pubblicazione: (2024)
• Leveraging Knowledge Distillation for Efficient Deep Reinforcement Learning in Resource-Constrained Environments
  di: Meng, Guanlin
  Pubblicazione: (2023)
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
  di: Yu, Qiying, et al.
  Pubblicazione: (2025)