PLMM: Personal Large Language Models on Mobile Devices

arXiv:2309.14726v2 Announce Type: replace-cross
Abstract: Inspired by Federated Learning, in this paper, we propose personal large models that are distilled from traditional large language models but more adaptive to local users' personal information such as education background and hobbies. We classify the large language models into three levels: the personal level, expert level and traditional level. The personal level models are adaptive to users' personal information. They encrypt the users' input and protect their privacy. The expert level models focus …

abstract arxiv cs.ai cs.ce cs.cl cs.cv cs.lg devices education expert federated learning hobbies information language language models large language large language models large models mobile mobile devices paper personal information type