Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate

Documenti analoghi

• Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning
  di: Ruan, Chi, et al.
  Pubblicazione: (2025)
• Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
  di: Wang, Yubo, et al.
  Pubblicazione: (2025)
• The Critique of Critique
  di: Sun, Shichao, et al.
  Pubblicazione: (2024)
• Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning
  di: Xi, Zhiheng, et al.
  Pubblicazione: (2025)
• Beyond Query-Level Comparison: Fine-Grained Reinforcement Learning for Text-to-SQL with Automated Interpretable Critiques
  di: Wang, Guifeng, et al.
  Pubblicazione: (2025)