From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation

Documenti analoghi

• Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
  di: Yang, Zixuan, et al.
  Pubblicazione: (2026)
• The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing
  di: Li, Muzhi, et al.
  Pubblicazione: (2024)
• NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
  di: Wang, Qichao, et al.
  Pubblicazione: (2025)
• OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation
  di: Zhang, Hanning, et al.
  Pubblicazione: (2025)
• ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning
  di: Hu, Minda, et al.
  Pubblicazione: (2026)