Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization

Documenti analoghi

• Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
  di: Dong, Guanting, et al.
  Pubblicazione: (2024)
• Training on the Benchmark Is Not All You Need
  di: Ni, Shiwen, et al.
  Pubblicazione: (2024)
• English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training
  di: Dhaliwal, Mehak, et al.
  Pubblicazione: (2026)
• Preference Ranking Optimization for Human Alignment
  di: Song, Feifan, et al.
  Pubblicazione: (2023)
• PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training
  di: Bobbili, Sarat Chandra, et al.
  Pubblicazione: (2025)