# PLMM: Personal Large Language Models on Mobile Devices

arXiv: https://arxiv.org/abs/2309.14726 · HTML: https://mlsanity.com/paper/2309.14726/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 56 references that are in the map.
- First posted on arXiv 26 Sep 2023.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Training Language Models with Language Feedback at Scale](https://mlsanity.com/paper/2303.16755/) (2023)
- [Side Window Filtering](https://mlsanity.com/paper/1905.07177/) (2019)
- [What do Large Language Models Learn about Scripts?](https://mlsanity.com/paper/2112.13834/) (2021)
- [Weighted Mean Curvature](https://mlsanity.com/paper/1903.07189/) (2019)
- [Fast and High-Quality Blind Multi-Spectral Image Pansharpening](https://mlsanity.com/paper/2103.09943/) (2021)
- [A Discrete Scheme for Computing Image's Weighted Gaussian Curvature](https://mlsanity.com/paper/2101.07927/) (2021)
- [Quarter Laplacian Filter for Edge Aware Image Processing](https://mlsanity.com/paper/2101.07933/) (2021)
- [TSSR: A Truncated and Signed Square Root Activation Function for Neural Networks](https://mlsanity.com/paper/2308.04832/) (2023)

## Abstract (arXiv)

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.