Saved in:
Bibliographic Details
Main Authors: Wang, Ganyu, Fang, Jinjie, Yin, Maxwell J., Gu, Bin, Chen, Xi, Wang, Boyu, Chang, Yi, Ling, Charles
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.14929
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Black-Box Discrete Prompt Learning is a prompt-tuning method that optimizes discrete prompts without accessing model parameters or gradients, making the prompt tuning on a cloud-based Large Language Model (LLM) feasible. Adapting federated learning to BDPL could further enhance prompt tuning performance by leveraging data from diverse sources. However, all previous research on federated black-box prompt tuning had neglected the substantial query cost associated with the cloud-based LLM service. To address this gap, we conducted a theoretical analysis of query efficiency within the context of federated black-box prompt tuning. Our findings revealed that degrading FedAvg to activate only one client per round, a strategy we called \textit{FedOne}, enabled optimal query efficiency in federated black-box prompt learning. Building on this insight, we proposed the FedOne framework, a federated black-box discrete prompt learning method designed to maximize query efficiency when interacting with cloud-based LLMs. We conducted numerical experiments on various aspects of our framework, demonstrating a significant improvement in query efficiency, which aligns with our theoretical results.