FewFedPIT：面向隐私保护的少样本联邦指令调优
PPFedIT: Towards Privacy-Preserving Federated Instruction Tuning with Few-shot Local Examples
AI总结：
针对联邦指令调优中数据稀缺、隐私易泄露的问题，提出含合成数据生成、参数隔离训练、本地聚合共享的FewFedPIT算法，在三个开源数据集上验证了其提升隐私保护与少样本性能的效果。
摘要：
指令调优已被证实是优化大语言模型（LLMs）生成符合人类偏好回复性能的关键技术。然而，收集多样化且高质量的指令数据用于此类调优存在显著障碍，在隐私规定严格的领域尤其如此。联邦指令调优（FedIT）作为一种有前景的解决方案应运而生，它整合多个数据所有者的协作训练，从而构建出具备隐私保护能力的学习模型。但FedIT面临着指令数据稀缺、易遭受训练数据提取攻击等局限。本文提出了一种新型联邦算法FewFedPIT，旨在同时提升联邦少样本学习的隐私保护水平与模型性能。FewFedPIT在客户端包含三个核心组件：（1）合成数据生成，利用LLMs的上下文学习能力自主生成合成数据，以此扩充本地数据库；（2）参数隔离训练，分别更新合成数据对应的公共参数与本地数据对应的私有参数，从而减轻合成数据的噪声影响；（3）本地聚合共享，在上传参数前混合公共参数与私有参数，有效防范数据提取攻击。在三个开源数据集上开展的大量实验证明了FewFedPIT的有效性，它增强了隐私保护能力，同时提升了联邦少样本学习的性能。
英文摘要：
Instruction tuning aligns large language models (LLMs) with human intentions but requires diverse, high-quality data that are difficult to collect in privacy-sensitive domains. Federated instruction tuning (FedIT) enables collaborative training across data owners, yet existing methods typically assume sufficient local data. In realistic few-shot settings, limited samples can cause overfitting, degrade performance, and increase vulnerability to training data extraction attacks. We propose PPFedIT, a federated algorithm that improves both model performance and privacy protection in federated few-shot learning. It comprises three client-side steps: (1) synthetic data generation, which uses LLMs to diversify and enrich local data; (2) parameter isolation training, which updates the shared global LLM on synthetic data and local LLMs on private local data to mitigate synthetic-data noise; and (3) local aggregation then sharing, which mixes global and local model parameters before uploading them for server aggregation to mitigate data extraction attacks. Experiments on three open-source datasets show that PPFedIT improves model performance by an average of 8.4% and reduces the risk of data extraction attacks by approximately 20% in challenging federated few-shot settings.
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。
