Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?

Documenti analoghi

• RuAG: Learned-rule-augmented Generation for Large Language Models
  di: Zhang, Yudi, et al.
  Pubblicazione: (2024)
• From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models
  di: Zhang, Jue, et al.
  Pubblicazione: (2025)
• PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments
  di: Schipper, Olivier, et al.
  Pubblicazione: (2025)
• Pretrain Value, Not Reward: Decoupled Value Policy Optimization
  di: Huang, Chenghua, et al.
  Pubblicazione: (2025)
• Self-Evolved Reward Learning for LLMs
  di: Huang, Chenghua, et al.
  Pubblicazione: (2024)