RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models

Documenti analoghi

• GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
  di: Zhang, Kaichen, et al.
  Pubblicazione: (2025)
• Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models
  di: Fan, Yuchen, et al.
  Pubblicazione: (2024)
• Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
  di: Hong, Yuzhong, et al.
  Pubblicazione: (2024)
• Multi-Turn Interactions for Text-to-SQL with Large Language Models
  di: Xiong, Guanming, et al.
  Pubblicazione: (2024)
• Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries
  di: Dragoi, Marius, et al.
  Pubblicazione: (2025)