▽Papers Written by Googlers ●07/31 02:12 Steerable Chatbots: Personalizing LLMs with Preference-Based Activation SteeringJessica BoTianyu XuIshan ChatterjeeKatrina PassarellaAce KulshresthaD Shin2025Preview Preview abstract As large language models (LLMs) improve in their capacity to serve as personal AI assistants, their ability to output uniquely tailored, personalized responses that align with the soft preferences of their use