arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.17694cs.LGcs.AI
收藏

AsynDBT:异步分布式双层调优用于高效上下文学习与大语言模型

AsynDBT: Asynchronous Distributed Bilevel Tuning for efficient In-Context Learning with Large Language Models

Xinjiang Key Laboratory of Intelligent Computing and Smart Applications, School of Software, Xinjiang University(新疆智能计算与智能应用重点实验室,软件学院,新疆大学);Department of Computer Science and Technology, Tongji University(计算机科学与技术系,同济大学);School of Information Science and Engineering, Zaozhuang University(信息科学与工程学院,枣庄大学);Xinjiang University, College of Geography and Remote Sensing Sciences(新疆大学,地理与遥感科学学院);Hochschule Bielefeld-University of Applied Sciences and Arts(比勒菲尔德应用科学与艺术大学);Xinjiang General Station of Exit and Entry Frontier Inspection(新疆出入境边防检查总站)

Hui Ma, Shaoyu Dou, Ya Liu, Fei Xing, Li Feng, Feng Pi

AI总结:

AsynDBT通过异步分布式双层调优优化上下文学习样本和提示片段,提升大语言模型在隐私保护和异构环境下的下游任务性能。

摘要:

随着大语言模型(LLMs)的快速发展,越来越多的应用利用基于云的LLM API来降低使用成本。然而,由于云模型的参数和梯度是无差别的,用户必须手动或使用启发式算法调整提示以干预LLM的输出,这需要昂贵的优化过程。上下文学习(ICL)最近出现作为一种有前途的范式,使LLM能够通过输入中提供的示例适应新任务,从而消除参数更新的需要。然而,ICL的发展常常受到高质量数据缺乏的阻碍,而这些数据通常是敏感的且难以共享。联邦学习(FL)提供了一个潜在的解决方案,通过在保护数据隐私的同时实现分布式LLM的协同训练。尽管如此,之前将ICL融入FL的方法在严重迟滞问题和异构非相同数据的挑战方面遇到了困难。为了解决这些问题,我们提出了一种异步分布式双层调优(AsynDBT)算法,该算法基于LLM的反馈优化上下文学习样本和提示片段,从而提高下游任务性能。得益于其分布式架构,AsynDBT提供了隐私保护并适应异构计算环境。此外,我们还提出了一个理论分析,确立了所提算法的收敛保证。在多个基准数据集上的广泛实验展示了AsynDBT的有效性和效率。

英文摘要:

With the rapid development of large language models (LLMs), an increasing number of applications leverage cloud-based LLM APIs to reduce usage costs. However, since cloud-based models' parameters and gradients are agnostic, users have to manually or use heuristic algorithms to adjust prompts for intervening LLM outputs, which requiring costly optimization procedures. In-context learning (ICL) has recently emerged as a promising paradigm that enables LLMs to adapt to new tasks using examples provided within the input, eliminating the need for parameter updates. Nevertheless, the advancement of ICL is often hindered by the lack of high-quality data, which is often sensitive and different to share. Federated learning (FL) offers a potential solution by enabling collaborative training of distributed LLMs while preserving data privacy. Despite this issues, previous FL approaches that incorporate ICL have struggled with severe straggler problems and challenges associated with heterogeneous non-identically data. To address these problems, we propose an asynchronous distributed bilevel tuning (AsynDBT) algorithm that optimizes both in-context learning samples and prompt fragments based on the feedback from the LLM, thereby enhancing downstream task performance. Benefiting from its distributed architecture, AsynDBT provides privacy protection and adaptability to heterogeneous computing environments. Furthermore, we present a theoretical analysis establishing the convergence guarantees of the proposed algorithm. Extensive experiments conducted on multiple benchmark datasets demonstrate the effectiveness and efficiency of AsynDBT.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑