# Personalized Collaborative Fine-Tuning for On-Device Large Language Models

arXiv: https://arxiv.org/abs/2404.09753 · HTML: https://mlsanity.com/paper/2404.09753/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 15 Apr 2024.

## Builds on (most cited first, 14 of 14)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Improving Federated Learning Personalization via Model Agnostic Meta Learning](https://mlsanity.com/paper/1909.12488/) (2019)
- [Personalized Federated Learning with First Order Model Optimization](https://mlsanity.com/paper/2012.08565/) (2020)
- [Towards Building the Federated GPT: Federated Instruction Tuning](https://mlsanity.com/paper/2305.05644/) (2023)
- [FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings](https://mlsanity.com/paper/2210.04620/) (2022)
- [Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization](https://mlsanity.com/paper/2310.15080/) (2023)
- [Two Directions for Clinical Data Generation with Large Language Models: Data-to-Label and Label-to-Data](https://mlsanity.com/paper/2401.06774/) (2023)
- [Find Your Friends: Personalized Federated Learning with the Right Collaborators](https://mlsanity.com/paper/2210.06597/) (2022)
- [Collaborative Learning via Prediction Consensus](https://mlsanity.com/paper/2305.18497/) (2023)

## Built on by (most cited first, 9 of 9)

- [A Survey of Personalized Large Language Models: Progress and Future Directions](https://mlsanity.com/paper/2502.11528/) (2025)
- [Low-Rank Adaptation for Foundation Models: A Comprehensive Review](https://mlsanity.com/paper/2501.00365/) (2024)
- [On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists](https://mlsanity.com/paper/2409.13931/) (2024)
- [CoBo: Collaborative Learning via Bilevel Optimization](https://mlsanity.com/paper/2409.05539/) (2024)
- [Learning Steerable Clarification Policies with Collaborative Self-play](https://mlsanity.com/paper/2512.04068/) (2025)
- [Revisiting Federated Fine-Tuning: A Single Communication Round is Enough for Foundation Models](https://mlsanity.com/paper/2412.04650/) (2024)
- [DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation Models](https://mlsanity.com/paper/2505.21382/) (2025)
- [Lorica: A Synergistic Fine-Tuning Framework for Advancing Personalized Adversarial Robustness](https://mlsanity.com/paper/2506.05402/) (2025)
- [PubSwap: Public-Data Off-Policy Coordination for Federated RLVR](https://mlsanity.com/paper/2604.12160/) (2026)

## Abstract (arXiv)

We explore on-device self-supervised collaborative fine-tuning of large language models with limited local data availability. Taking inspiration from the collaborative learning community, we introduce three distinct trust-weighted gradient aggregation schemes: weight similarity-based, prediction similarity-based and validation performance-based. To minimize communication overhead, we integrate Low-Rank Adaptation (LoRA) and only exchange LoRA weight updates. Our protocols, driven by prediction and performance metrics, surpass both FedAvg and local fine-tuning methods, which is particularly evident in realistic scenarios with more diverse local data distributions. The results underscore the effectiveness of our approach in addressing heterogeneity and scarcity within local datasets.