Fine Tuning on False Facts

AI & ML interests

None defined yet.

Recent Activity

mollejasaurio  authored a paper 4 days ago

Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment

sohv  authored a paper 27 days ago

On the Non-Identifiability of Steering Vectors in Large Language Models

sohv  updated a model about 1 month ago

false-facts-finetuning/realistic-scenarios

View all activity

Team members 3