Saved in:
Bibliographic Details
Main Authors: Chen, Zeyu, Ji, Yun, Wang, Bowen, Shi, Liwen, Zeng, Zijie, Zhang, Sheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.00543
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918152334475264
author Chen, Zeyu
Ji, Yun
Wang, Bowen
Shi, Liwen
Zeng, Zijie
Zhang, Sheng
author_facet Chen, Zeyu
Ji, Yun
Wang, Bowen
Shi, Liwen
Zeng, Zijie
Zhang, Sheng
contents Large language models (LLMs) show great promise in healthcare, but their applications are hindered by data privacy restrictions and the challenges of cross-institution collaboration. Sensitive medical data cannot be centralized, while non-independent and identically distributed (non-IID) characteristics across institutions further complicate convergence and fairness. To address these issues, we present a federated fine-tuning approach based on Low-Rank Adaptation (LoRA), enabling privacy-preserving knowledge flow across institutions. The method iteratively combines local LoRA adaptation with global parameter aggregation, allowing efficient knowledge sharing without exposing raw data. A blockchain identity scheme is used for identifying individual LLM in such a distributed network. We evaluate this approach on heterogeneous and highly non-IID medical text datasets, where experiments demonstrate that federated LoRA not only enhances cross-client generalization but also improves the performance of the weakest client, achieving stable convergence and fairer outcomes. These findings highlight federated LoRA fine-tuning as a practical and effective paradigm for adapting LLMs in healthcare, offering a new path for multi-center medical AI collaboration.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00543
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Flow of Knowledge: Federated Fine-Tuning of LLMs in Healthcare under Non-IID Conditions
Chen, Zeyu
Ji, Yun
Wang, Bowen
Shi, Liwen
Zeng, Zijie
Zhang, Sheng
Computational Engineering, Finance, and Science
Large language models (LLMs) show great promise in healthcare, but their applications are hindered by data privacy restrictions and the challenges of cross-institution collaboration. Sensitive medical data cannot be centralized, while non-independent and identically distributed (non-IID) characteristics across institutions further complicate convergence and fairness. To address these issues, we present a federated fine-tuning approach based on Low-Rank Adaptation (LoRA), enabling privacy-preserving knowledge flow across institutions. The method iteratively combines local LoRA adaptation with global parameter aggregation, allowing efficient knowledge sharing without exposing raw data. A blockchain identity scheme is used for identifying individual LLM in such a distributed network. We evaluate this approach on heterogeneous and highly non-IID medical text datasets, where experiments demonstrate that federated LoRA not only enhances cross-client generalization but also improves the performance of the weakest client, achieving stable convergence and fairer outcomes. These findings highlight federated LoRA fine-tuning as a practical and effective paradigm for adapting LLMs in healthcare, offering a new path for multi-center medical AI collaboration.
title Flow of Knowledge: Federated Fine-Tuning of LLMs in Healthcare under Non-IID Conditions
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2510.00543