# Can Public Large Language Models Help Private Cross-device Federated Learning?

arXiv: https://arxiv.org/abs/2305.12132 · HTML: https://mlsanity.com/paper/2305.12132/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 60 references that are in the map.
- First posted on arXiv 20 May 2023.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [Differentially Private Fine-tuning of Language Models](https://mlsanity.com/paper/2110.06500/) (2021)
- [A Field Guide to Federated Optimization](https://mlsanity.com/paper/2107.06917/) (2021)
- [Depth-Adaptive Transformer](https://mlsanity.com/paper/1910.10073/) (2019)
- [Differentially Private Learning with Adaptive Clipping](https://mlsanity.com/paper/1905.03871/) (2019)
- [Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning](https://mlsanity.com/paper/2002.08307/) (2020)
- [Practical and Private (Deep) Learning without Sampling or Shuffling](https://mlsanity.com/paper/2103.00039/) (2021)
- [Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning](https://mlsanity.com/paper/2210.08090/) (2022)
- [Training Production Language Models without Memorizing User Data](https://mlsanity.com/paper/2009.10031/) (2020)
- [Automated Scalable Bayesian Inference via Hilbert Coresets](https://mlsanity.com/paper/1710.05053/) (2017)
- [Federated Learning Of Out-Of-Vocabulary Words](https://mlsanity.com/paper/1903.10635/) (2019)
- [Public Data-Assisted Mirror Descent for Private Model Training](https://mlsanity.com/paper/2112.00193/) (2021)
- [Differentially Private Bias-Term Fine-tuning of Foundation Models](https://mlsanity.com/paper/2210.00036/) (2022)
- [Differentially Private Language Models Benefit from Public Pre-training](https://mlsanity.com/paper/2009.05886/) (2020)

## Built on by (most cited first, 30 of 30)

- [OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning](https://mlsanity.com/paper/2402.06954/) (2024)
- [Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources](https://mlsanity.com/paper/2402.11505/) (2024)
- [Federated Learning of Gboard Language Models with Differential Privacy](https://mlsanity.com/paper/2305.18465/) (2023)
- [FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models](https://mlsanity.com/paper/2310.10049/) (2023)
- [SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models](https://mlsanity.com/paper/2407.00952/) (2024)
- [Privacy in Large Language Models: Attacks, Defenses and Future Directions](https://mlsanity.com/paper/2310.10383/) (2023)
- [Privacy-Preserving Instructions for Aligning Large Language Models](https://mlsanity.com/paper/2402.13659/) (2024)
- [The Future of Large Language Model Pre-training is Federated](https://mlsanity.com/paper/2405.10853/) (2024)
- [PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs](https://mlsanity.com/paper/2406.02958/) (2024)
- [Federated Large Language Models: Current Progress and Future Directions](https://mlsanity.com/paper/2409.15723/) (2024)
- [FwdLLM: Efficient FedLLM using Forward Gradient](https://mlsanity.com/paper/2308.13894/) (2023)
- [GPT-FL: Generative Pre-trained Model-Assisted Federated Learning](https://mlsanity.com/paper/2306.02210/) (2023)
- [Grounding Foundation Models through Federated Transfer Learning: A General Framework](https://mlsanity.com/paper/2311.17431/) (2023)
- [Prompt Public Large Language Models to Synthesize Data for Private On-device Applications](https://mlsanity.com/paper/2404.04360/) (2024)
- [Federated Distillation: A Survey](https://mlsanity.com/paper/2404.08564/) (2024)
- [Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning](https://mlsanity.com/paper/2310.04627/) (2023)
- [Analysis of Privacy Leakage in Federated Large Language Models](https://mlsanity.com/paper/2403.04784/) (2024)
- [A Hassle-free Algorithm for Private Learning in Practice: Don't Use Tree Aggregation, Use BLTs](https://mlsanity.com/paper/2408.08868/) (2024)
- [Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.19101/) (2025)
- [AugFL: Augmenting Federated Learning with Pretrained Models](https://mlsanity.com/paper/2503.02154/) (2025)
- [Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA](https://mlsanity.com/paper/2503.03920/) (2025)
- [Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks](https://mlsanity.com/paper/2504.17421/) (2025)
- [Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice](https://mlsanity.com/paper/2510.12595/) (2025)
- [Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data](https://mlsanity.com/paper/2405.14212/) (2024)
- [Personalized Federated Learning via ADMM with Moreau Envelope](https://mlsanity.com/paper/2311.06756/) (2023)
- [Federated Learning with New Knowledge: Fundamentals, Advances, and Futures](https://mlsanity.com/paper/2402.02268/) (2024)
- [On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness](https://mlsanity.com/paper/2407.16397/) (2024)
- [A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2508.19620/) (2025)
- [Resource-Adaptive Federated Text Generation with Differential Privacy](https://mlsanity.com/paper/2603.07027/) (2026)
- [PubSwap: Public-Data Off-Policy Coordination for Federated RLVR](https://mlsanity.com/paper/2604.12160/) (2026)

## Abstract (arXiv)

We study (differentially) private federated learning (FL) of language models. The language models in cross-device FL are relatively small, which can be trained with meaningful formal user-level differential privacy (DP) guarantees when massive parallelism in training is enabled by the participation of a moderate size of users. Recently, public data has been used to improve privacy-utility trade-offs for both large and small language models. In this work, we provide a systematic study of using large-scale public data and LLMs to help differentially private training of on-device FL models, and further improve the privacy-utility tradeoff by techniques of distillation. Moreover, we propose a novel distribution matching algorithm with theoretical grounding to sample public data close to private data distribution, which significantly improves the sample efficiency of (pre-)training on public data. The proposed method is efficient and effective for training private models by taking advantage of public data, especially for customized on-device architectures that do not have ready-to-use pre-trained models.