Beyond Preferences: Learning Alignment Principles Grounded in Human Reasons and Values

Documenti analoghi

• Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale
  di: Bell, Henry, et al.
  Pubblicazione: (2026)
• ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference
  di: Cai, Tianchi, et al.
  Pubblicazione: (2023)
• Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisition
  di: Bao, Yuwei, et al.
  Pubblicazione: (2023)
• Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input
  di: Peng, Andi, et al.
  Pubblicazione: (2024)
• MaxMin-RLHF: Alignment with Diverse Human Preferences
  di: Chakraborty, Souradip, et al.
  Pubblicazione: (2024)