← authors · overview

• Arithmetic Control Of Llms For Diverse User Preferences: Directional Preference Alignment With Multi-objective Rewards
  2024 · 140 citations
• LISA: Layerwise Importance Sampling For Memory-efficient Large Language Model Fine-tuning
  2024 · 106 citations
• Sayself: Teaching Llms To Express Confidence With Self-reflective Rationales
  2024 · 95 citations