Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization

Documenti analoghi

• Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models
  di: Liu, Biao, et al.
  Pubblicazione: (2025)
• Negative-Prompt-driven Alignment for Generative Language Model
  di: Qiao, Shiqi, et al.
  Pubblicazione: (2024)
• Progressively Label Enhancement for Large Language Model Alignment
  di: Liu, Biao, et al.
  Pubblicazione: (2024)
• VRM: Teaching Reward Models to Understand Authentic Human Preferences
  di: Liu, Biao, et al.
  Pubblicazione: (2026)
• Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment
  di: Xu, Wenzhe, et al.
  Pubblicazione: (2026)