Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs.
Pranav Bhandari, Nicolas Fay, Sanjeevan Selvaganapathy, Amitava Datta, Usman Naseem, Mehwish Nasim
Browse the full EACL paper archive.
Pranav Bhandari, Nicolas Fay, Sanjeevan Selvaganapathy, Amitava Datta, Usman Naseem, Mehwish Nasim
Browse the full EACL paper archive.