MarginSel : Max-Margin Demonstration Selection for LLMs

Documenti analoghi

• Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection
  di: Julistiono, Addison Kristanto, et al.
  Pubblicazione: (2024)
• Meta-Sel: Efficient Demonstration Selection for In-Context Learning via Supervised Meta-Learning
  di: Wang, Xubin, et al.
  Pubblicazione: (2026)
• Socratic Students: Teaching Language Models to Learn by Asking Questions
  di: Ambati, Rajeev Bhatt, et al.
  Pubblicazione: (2025)
• Larger or Smaller Reward Margins to Select Preferences for Alignment?
  di: Huang, Kexin, et al.
  Pubblicazione: (2025)
• Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion
  di: Zaman, Kerem, et al.
  Pubblicazione: (2023)