Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning

• URL: http://arxiv.org/abs/2605.13936v1
• Date: Wed, 13 May 2026 16:20:33 GMT
• Title: Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning
• Abstract summary: Much of the world's most valuable information is private, especially in highly regulated sectors such as healthcare and finance.<n>In this paper, we demonstrate a practical approach to unlocking private and distributed institutional data for large language models (LLMs) adaptation.<n>Built on the Sherpa.ai Federated Learning platform, our framework enables nodes to jointly fine-tune a shared LLM without exchanging private data.
• Score: 0.44333156307871574
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The recent success of large language models (LLMs) has been largely driven by vast public datasets. However, the next frontier for LLM development lies beyond public data. Much of the world's most valuable information is private, especially in highly regulated sectors such as healthcare and finance, where data include patient histories or customer communications. Unlocking this data could represent a major leap forward, enabling LLMs with deeper domain expertise and stronger real-world utility. Yet, these data cannot be shared because they are distributed across institutions and constrained by privacy, regulatory, and organizational barriers. Moreover, institutional datasets are typically non-independent and identically distributed (non-IID), differing across sites in population characteristics, data modalities, documentation patterns, and task-specific label distributions. In this paper, we demonstrate a practical approach to unlocking private and distributed institutional data for LLM adaptation through federated collaboration across data silos. Built on the Sherpa.ai Federated Learning platform, our framework enables nodes to jointly fine-tune a shared LLM without exchanging private data. We evaluate this approach through a cross-domain benchmark in healthcare and finance, using four closed-ended question answering and classification datasets: MedQA, MedMCQA, FPB, and FiQA-SA. We compare three parameter-efficient fine-tuning (PEFT) strategies-LoRA, QLoRA, and IA3-across pretrained backbones under non-IID settings reflecting institutional data heterogeneity. Our results show that federated fine-tuning performs close to centralized training and outperforms isolated single-institution learning. From a Green AI perspective, QLoRA and IA3 improve efficiency with limited accuracy degradation, supporting federated PEFT as a viable approach for adapting LLMs where data cannot be shared.

Related papers

• FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment [55.97027207627]
  Fed PDPO (Federated Personalized Direct Preference Optimization) is a personalized framework for preference alignment of large language models (LLMs)<n>It adopts a parameter-efficient fine-tuning architecture where each client maintains a frozen pretrained LLM backbone augmented with a Low-Rank Adaptation (LoRA) adapter, enabling communication-efficient aggregation.<n>Experiments on multiple preference datasets demonstrate state-of-the-art performance, achieving up to 4.80% average accuracy improvements in federated intra-domain and cross-domain settings.
  arXiv  Detail & Related papers  (2026-03-20T08:24:49Z)
• Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation [20.37072541084284]
  Federated learning (FL) enables clients to retain local data while sharing only model parameters for collaborative training.<n>We show that attackers can still extract training data from the global model, even using straightforward generation methods.<n>We introduce an enhanced attack strategy tailored to FL, which tracks global model updates during training to intensify privacy leakage.
  arXiv  Detail & Related papers  (2025-09-25T02:28:08Z)
• Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models [32.059157903736754]
  Large Language Models (LLMs) increasingly leverage Federated Learning (FL) to utilize private, task-specific datasets for fine-tuning.<n>We introduce Oblivionis, a lightweight learning and unlearning framework that enables clients to selectively remove specific private data.
  arXiv  Detail & Related papers  (2025-08-12T12:02:53Z)
• FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models [43.62847972139202]
  Large Language Models (LLMs) have achieved state-of-the-art results across diverse domains, yet their development remains reliant on vast amounts of publicly available data.<n>This work lays the foundation for developing privacy-preserving, domain-specialized LLMs for real-world applications.
  arXiv  Detail & Related papers  (2025-06-03T14:54:12Z)
• Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions [59.5243730853157]
  Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets.<n>This article conducts a comparative analysis of three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues.
  arXiv  Detail & Related papers  (2025-01-08T11:37:06Z)
• LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation [50.375567142250446]
  Large language models (LLMs), trained on vast corpora, have shown strong potential in data generation.<n>We propose a novel framework, LLM-Forest, which introduces a "forest" of few-shot prompt learning LLM "trees" with their outputs aggregated via confidence-based weighted voting.<n>This framework is established on a new concept of bipartite information graphs to identify high-quality relevant neighboring entries with both feature and value granularity.
  arXiv  Detail & Related papers  (2024-10-28T20:42:46Z)
• Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data [53.70870879858533]
  We introduce a Federated Domain-specific Knowledge Transfer framework. It enables domain-specific knowledge transfer from LLMs to SLMs while preserving clients' data privacy. The proposed FDKT framework consistently and greatly improves SLMs' task performance by around 5% with a privacy budget of less than 10.
  arXiv  Detail & Related papers  (2024-05-23T06:14:35Z)
• FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning [54.26614091429253]
  Federated instruction tuning (FedIT) is a promising solution, by consolidating collaborative training across multiple data owners. FedIT encounters limitations such as scarcity of instructional data and risk of exposure to training data extraction attacks. We propose FewFedPIT, designed to simultaneously enhance privacy protection and model performance of federated few-shot learning.
  arXiv  Detail & Related papers  (2024-03-10T08:41:22Z)
• Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning [32.52811740662061]
  This article introduces DP-LoRA, a novel federated learning algorithm tailored for large language models (LLMs) DP-LoRA preserves data privacy by employing a Gaussian mechanism that adds noise in weight updates, maintaining individual data privacy while facilitating collaborative model training.
  arXiv  Detail & Related papers  (2023-12-29T06:50:38Z)
• FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning [70.38817963253034]
  This paper first discusses these challenges of federated fine-tuning LLMs, and introduces our package FS-LLM as a main contribution. We provide comprehensive federated parameter-efficient fine-tuning algorithm implementations and versatile programming interfaces for future extension in FL scenarios. We conduct extensive experiments to validate the effectiveness of FS-LLM and benchmark advanced LLMs with state-of-the-art parameter-efficient fine-tuning algorithms in FL settings.
  arXiv  Detail & Related papers  (2023-09-01T09:40:36Z)
• Benchmarking FedAvg and FedCurv for Image Classification Tasks [1.376408511310322]
  This paper focuses on the problem of statistical heterogeneity of the data in the same federated network. Several Federated Learning algorithms, such as FedAvg, FedProx and Federated Curvature (FedCurv) have already been proposed. As a side product of this work, we release the non-IID version of the datasets we used so to facilitate further comparisons from the FL community.
  arXiv  Detail & Related papers  (2023-03-31T10:13:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.