Collections
Discover the best community collections!
Collections trending this week
-
Scalable Extraction of Training Data from (Production) Language Models
Paper • 2311.17035 • Published • 3 -
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Paper • 2401.05566 • Published • 30 -
Exploiting Novel GPT-4 APIs
Paper • 2312.14302 • Published • 13 -
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Paper • 2404.13208 • Published • 40
-
Scalable Extraction of Training Data from (Production) Language Models
Paper • 2311.17035 • Published • 3 -
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Paper • 2401.05566 • Published • 30 -
Exploiting Novel GPT-4 APIs
Paper • 2312.14302 • Published • 13 -
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Paper • 2404.13208 • Published • 40