← authors · overview

• On The Opportunities And Risks Of Foundation Models
  2021 · 6272 citations
• Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
  2023 · 1086 citations
• Legalbench: A Collaboratively Built Benchmark For Measuring Legal Reasoning In Large Language Models
  2023 · 365 citations
• Safety Alignment Should Be Made More Than Just A Few Tokens Deep
  2024 · 360 citations