mlsanityData to 14 Oct 2026

PAE MobiLLM: Privacy-Aware and Efficient LLM Fine-Tuning on the Mobile Device via Additive Side-Tuning

arXiv 2507.01216 ↗First posted 1 Jul 2025cs.LG cs.CRcited by 4

Not on the map. Why?

Abstract (arXiv)

There is a huge gap between numerous intriguing applications fostered by on-device large language model (LLM) fine-tuning (FT) from fresh mobile data and the limited resources of a mobile device. While existing server-assisted methods (e.g., split learning or side-tuning) may enable LLM FT on the local mobile device, they suffer from heavy communication burdens of activation transmissions, and may disclose data and labels to the server. To address those issues, we develop PAE MobiLLM, a a privacy-aware and efficient LLM FT method which can be deployed on the mobile device via server-assisted additive side-tuning. To further accelerate FT convergence and improve computing efficiency, PAE MobiLLM integrates activation caching on the server side, which allows the server to reuse historical activations and saves the mobile device from repeatedly computing forward passes for the recurring data samples. Besides, to reduce communication cost, PAE MobiLLM develops an activation shortcut that transmits only the token involved in the loss calculation instead of full activation matrices to guide the side network tuning. Last but not least, PAE MobiLLM introduces the additive adapter side-network design which makes the server train the adapter modules based on device-defined prediction differences rather than raw ground-truth labels. In this way, the server can only assist device-defined side-network computing, and learn nothing about data and labels. Extensive experimental results demonstrate PAE MobiLLM's superiority.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

23 of 37 references.

References · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  6. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  7. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  8. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  9. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  10. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  11. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  12. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,245
11 more
  1. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 1,001
  2. 2018Neural Network Acceptability Judgmentscited by 958
  3. 2018Distributed learning of deep neural network over multiple agentscited by 279
  4. 2022LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learningcited by 230
  5. 2021DialogSum: A Real-Life Scenario Dialogue Summarization Datasetcited by 183
  6. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  7. 2020To Talk or to Work: Flexible Communication Compression for Energy Efficient Federated Learning over Heterogeneous Mobile Edge Devicescited by 46
  8. 2024Time-, Memory- and Parameter-Efficient Visual Adaptationcited by 28
  9. 2023FwdLLM: Efficient FedLLM using Forward Gradientcited by 26
  10. 2025MobiLLM: Enabling LLM Fine-Tuning on the Mobile Device via Server Assisted Side Tuningcited by 10
  11. 2023Confidant: Customizing Transformer-based LLMs via Collaborative Edge Trainingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2026PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Trainingcited by 7
  2. 2025MobileFineTuner: A Mobile-Native Framework for On-Device LLM Fine-Tuning in Real-World Embedded AI Applicationscited by 2
  3. 2025Fed MobiLLM: Efficient Federated LLM Fine-Tuning over Heterogeneous Mobile Devices via Server Assisted Side-Tuningcited by 1
  4. 2026Fine-Tuning a 3B-Parameter LLM on a Smartphone: Characterizing Sustained Trainingcited by 0