PLMM: Personal Large Language Models on Mobile Devices

TL;DR

This paper introduces personal large language models tailored for mobile devices that adapt to individual users' data while ensuring privacy, enabling real-time, high-quality language and vision applications.

Contribution

The paper proposes a novel classification of large language models into personal, expert, and traditional levels, with a focus on privacy, adaptability, and deployment on mobile devices.

Findings

Personal models protect user privacy through encryption.

Models are small enough for mobile deployment.

System supports real-time, high-quality language and vision tasks.

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 on merging specific knowledge such as finance, IT and art. The traditional models focus on the universal knowledge discovery and upgrading the expert models. In such classifications, the personal models directly interact with the user. For the whole system, the personal models have users' (encrypted) personal information. Moreover, such models must be small enough to be performed on personal computers or mobile devices. Finally, they also have to response in real-time for better user experience and produce high quality results. The proposed personal large models can be applied in a wide range of applications such as language and vision tasks.