-
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Paper • 2401.05566 • Published • 30 -
On the Societal Impact of Open Foundation Models
Paper • 2403.07918 • Published • 17 -
JudgeLM: Fine-tuned Large Language Models are Scalable Judges
Paper • 2310.17631 • Published • 35 -
Instruction Tuning for Large Language Models: A Survey
Paper • 2308.10792 • Published • 1
Jonathan Jin
jinnovation
AI & ML interests
Ethical AI; distributed training; model optimization/compilation
Organizations
-
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Paper • 2401.05566 • Published • 30 -
On the Societal Impact of Open Foundation Models
Paper • 2403.07918 • Published • 17 -
JudgeLM: Fine-tuned Large Language Models are Scalable Judges
Paper • 2310.17631 • Published • 35 -
Instruction Tuning for Large Language Models: A Survey
Paper • 2308.10792 • Published • 1