24 citations · 24 across the 4 of their papers we have counts for
1 paper · 2 filters
Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad +2
Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment. Existing steering methods, such as Contrastive Activation Addition (CAA), ty…