Online Personalizing White-box LLMs Generation with Neural Bandits

arXiv:2404.16115v1 Announce Type: cross
Abstract: The advent of personalized content generation by LLMs presents a novel challenge: how to efficiently adapt text to meet individual preferences without the unsustainable demand of creating a unique model for each user. This study introduces an innovative online method that employs neural bandit algorithms to dynamically optimize soft instruction embeddings based on user feedback, enhancing the personalization of open-ended text generation by white-box LLMs. Through rigorous experimentation on various tasks, we demonstrate significant performance …

abstract adapt algorithms arxiv box challenge content generation cs.ai cs.cl cs.lg demand llms novel personalized study text type unique