Length-Controlled Margin-Based Preference Optimization without Reference Model

Documenti analoghi

• Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models
  di: Li, Jinzhe, et al.
  Pubblicazione: (2025)
• Large Language Model Evaluation via Matrix Nuclear-Norm
  di: Li, Yahan, et al.
  Pubblicazione: (2024)
• A Survey of RWKV
  di: Li, Zhiyuan, et al.
  Pubblicazione: (2024)
• Language Models can Evaluate Themselves via Probability Discrepancy
  di: Xia, Tingyu, et al.
  Pubblicazione: (2024)
• ORPO: Monolithic Preference Optimization without Reference Model
  di: Hong, Jiwoo, et al.
  Pubblicazione: (2024)