RL Fine-Tuning Heals OOD Forgetting in SFT

Documenti analoghi

• Rotation-Preserving Supervised Fine-Tuning
  di: Jin, Hangzhan, et al.
  Pubblicazione: (2026)
• RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs
  di: Jin, Hangzhan, et al.
  Pubblicazione: (2025)
• CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models
  di: Jin, Hangzhan, et al.
  Pubblicazione: (2025)
• Higher-Order Transformers With Kronecker-Structured Attention
  di: Omranpour, Soroush, et al.
  Pubblicazione: (2024)
• Understanding Behavioral Metric Learning: A Large-Scale Study on Distracting Reinforcement Learning Environments
  di: Luo, Ziyan, et al.
  Pubblicazione: (2025)