Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference

Documenti analoghi

• EEG-Based Brain-LLM Interface for Human Preference Aligned Generation
  di: Zhang, Junzi, et al.
  Pubblicazione: (2026)
• Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models
  di: Zhang, Fuxiang, et al.
  Pubblicazione: (2024)
• Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
  di: Ma, Qiyao, et al.
  Pubblicazione: (2026)
• Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
  di: Li, Yi-Chen, et al.
  Pubblicazione: (2024)
• Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
  di: Zhang, Qingru, et al.
  Pubblicazione: (2025)