AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation

Documenti analoghi

• KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models
  di: Zhang, Songming, et al.
  Pubblicazione: (2026)
• A Dual-Space Framework for General Knowledge Distillation of Large Language Models
  di: Zhang, Xue, et al.
  Pubblicazione: (2025)
• Dual-Space Knowledge Distillation for Large Language Models
  di: Zhang, Songming, et al.
  Pubblicazione: (2024)
• Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation
  di: Zhang, Songming, et al.
  Pubblicazione: (2023)
• Evolutionary Contrastive Distillation for Language Model Alignment
  di: Katz-Samuels, Julian, et al.
  Pubblicazione: (2024)