Cem Anil

anilcem's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 6 months ago

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Paper • 2501.18837 • Published Jan 31 • 10

authored a paper over 1 year ago

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Paper • 2401.05566 • Published Jan 10, 2024 • 30

authored a paper almost 2 years ago

Studying Large Language Model Generalization with Influence Functions

Paper • 2308.03296 • Published Aug 7, 2023 • 13