Branch-Solve-Merge Improves Large Language Model Evaluation and Generation

Documenti analoghi

• ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
  di: Chen, Justin Chih-Yao, et al.
  Pubblicazione: (2023)
• Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
  di: Saha, Swarnadeep, et al.
  Pubblicazione: (2025)
• System-1.x: Learning to Balance Fast and Slow Planning with Language Models
  di: Saha, Swarnadeep, et al.
  Pubblicazione: (2024)
• J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning
  di: Whitehouse, Chenxi, et al.
  Pubblicazione: (2025)
• The Majority is not always right: RL training for solution aggregation
  di: Zhao, Wenting, et al.
  Pubblicazione: (2025)