The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning

Documenti analoghi

• SimPO: Simple Preference Optimization with a Reference-Free Reward
  di: Meng, Yu, et al.
  Pubblicazione: (2024)
• InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
  di: Wei, Zhepei, et al.
  Pubblicazione: (2024)
• You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
  di: Wei, Zhepei, et al.
  Pubblicazione: (2026)
• Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training
  di: Zhong, Zexuan, et al.
  Pubblicazione: (2024)
• Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
  di: Xia, Mengzhou, et al.
  Pubblicazione: (2023)