LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yingyi, Jia, Pengyue, Li, Xianneng, Xu, Derong, Wang, Maolin, Wang, Yichao, Du, Zhaocheng, Guo, Huifeng, Liu, Yong, Tang, Ruiming, Zhao, Xiangyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912752720674816
author Zhang, Yingyi
Jia, Pengyue
Li, Xianneng
Xu, Derong
Wang, Maolin
Wang, Yichao
Du, Zhaocheng
Guo, Huifeng
Liu, Yong
Tang, Ruiming
Zhao, Xiangyu
author_facet Zhang, Yingyi
Jia, Pengyue
Li, Xianneng
Xu, Derong
Wang, Maolin
Wang, Yichao
Du, Zhaocheng
Guo, Huifeng
Liu, Yong
Tang, Ruiming
Zhao, Xiangyu
contents Cloud-device collaboration leverages on-cloud Large Language Models (LLMs) for handling public user queries and on-device Small Language Models (SLMs) for processing private user data, collectively forming a powerful and privacy-preserving solution. However, existing approaches often fail to fully leverage the scalable problem-solving capabilities of on-cloud LLMs while underutilizing the advantage of on-device SLMs in accessing and processing personalized data. This leads to two interconnected issues: 1) Limited utilization of the problem-solving capabilities of on-cloud LLMs, which fail to align with personalized user-task needs, and 2) Inadequate integration of user data into on-device SLM responses, resulting in mismatches in contextual user information. In this paper, we propose a Leader-Subordinate Retrieval framework for Privacy-preserving cloud-device collaboration (LSRP), a novel solution that bridges these gaps by: 1) enhancing on-cloud LLM guidance to on-device SLM through a dynamic selection of task-specific leader strategies named as user-to-user retrieval-augmented generation (U-U-RAG), and 2) integrating the data advantages of on-device SLMs through small model feedback Direct Preference Optimization (SMFB-DPO) for aligning the on-cloud LLM with the on-device SLM. Experiments on two datasets demonstrate that LSRP consistently outperforms state-of-the-art baselines, significantly improving question-answer relevance and personalization, while preserving user privacy through efficient on-device retrieval. Our code is available at: https://github.com/Applied-Machine-Learning-Lab/LSRP.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05031
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration
Zhang, Yingyi
Jia, Pengyue
Li, Xianneng
Xu, Derong
Wang, Maolin
Wang, Yichao
Du, Zhaocheng
Guo, Huifeng
Liu, Yong
Tang, Ruiming
Zhao, Xiangyu
Information Retrieval
Cloud-device collaboration leverages on-cloud Large Language Models (LLMs) for handling public user queries and on-device Small Language Models (SLMs) for processing private user data, collectively forming a powerful and privacy-preserving solution. However, existing approaches often fail to fully leverage the scalable problem-solving capabilities of on-cloud LLMs while underutilizing the advantage of on-device SLMs in accessing and processing personalized data. This leads to two interconnected issues: 1) Limited utilization of the problem-solving capabilities of on-cloud LLMs, which fail to align with personalized user-task needs, and 2) Inadequate integration of user data into on-device SLM responses, resulting in mismatches in contextual user information. In this paper, we propose a Leader-Subordinate Retrieval framework for Privacy-preserving cloud-device collaboration (LSRP), a novel solution that bridges these gaps by: 1) enhancing on-cloud LLM guidance to on-device SLM through a dynamic selection of task-specific leader strategies named as user-to-user retrieval-augmented generation (U-U-RAG), and 2) integrating the data advantages of on-device SLMs through small model feedback Direct Preference Optimization (SMFB-DPO) for aligning the on-cloud LLM with the on-device SLM. Experiments on two datasets demonstrate that LSRP consistently outperforms state-of-the-art baselines, significantly improving question-answer relevance and personalization, while preserving user privacy through efficient on-device retrieval. Our code is available at: https://github.com/Applied-Machine-Learning-Lab/LSRP.
title LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration
topic Information Retrieval
url https://arxiv.org/abs/2505.05031