Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models

Documenti analoghi

• Curriculum Learning-Guided Progressive Distillation in Large Language Models
  di: Cao, Jincheng, et al.
  Pubblicazione: (2026)
• The Linear Representation Hypothesis and the Geometry of Large Language Models
  di: Park, Kiho, et al.
  Pubblicazione: (2023)
• Compositional Steering of Large Language Models with Steering Tokens
  di: Radevski, Gorjan, et al.
  Pubblicazione: (2026)
• Prompting Fairness: Integrating Causality to Debias Large Language Models
  di: Li, Jingling, et al.
  Pubblicazione: (2024)
• A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
  di: Yuan, Hui, et al.
  Pubblicazione: (2024)