Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning

Documenti analoghi

• On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
  di: Huang, Kexin, et al.
  Pubblicazione: (2026)
• RePO: Understanding Preference Learning Through ReLU-Based Optimization
  di: Wu, Junkang, et al.
  Pubblicazione: (2025)
• Larger or Smaller Reward Margins to Select Preferences for Alignment?
  di: Huang, Kexin, et al.
  Pubblicazione: (2025)
• $β$-DPO: Direct Preference Optimization with Dynamic $β$
  di: Wu, Junkang, et al.
  Pubblicazione: (2024)
• AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
  di: Wu, Junkang, et al.
  Pubblicazione: (2024)