FedCoT：面向大语言模型的联邦思维链蒸馏
FedCoT: Federated Chain-of-Thought Distillation for Large Language Models
AI总结：
FedCoT提出一种联邦思维链蒸馏框架，在保护客户端数据隐私的前提下，通过扰动提示和两种指数机制策略将大语言模型知识高效迁移至小语言模型，并在文本生成任务中验证了其有效性。
摘要：
大语言模型（LLMs）已成为人工智能领域的一股变革性力量，在各类任务中展现出卓越的能力。然而，它们在资源受限环境中的部署以及对用户数据隐私的担忧构成了重大挑战。相比之下，小语言模型（SLMs）具有计算效率优势，但性能往往较差。为解决这些问题，我们提出了FedCoT，这是一个联邦框架，旨在实现从LLMs到SLMs的思维链（Chain-of-Thought, CoT）知识蒸馏，同时确保客户端数据隐私得到保护。FedCoT在遵守隐私要求的前提下，确保知识从高性能服务器上的LLM安全高效地转移到资源受限客户端上的SLM。该框架利用通过CoT方法生成的扰动提示和推理依据，在多任务学习框架内提升客户端SLM的性能，同时不损害用户数据隐私。我们提出了两种隐私保护策略：指数机制策略和自适应指数机制策略，它们在用户提示隐私与推理依据可用性之间取得平衡。在多种文本生成任务上的实证评估表明，FedCoT能够有效训练特定任务的SLM，在优先保护数据隐私的同时提升性能。我们的代码已贡献给FATE开源项目，现已在 https://github.com/FederatedAI/FATE-LLM/tree/main/python/fate_llm/algo/fedcot 公开访问。
英文摘要：
Large Language Models (LLMs) have emerged as a transformative force in artificial intelligence, demonstrating exceptional proficiency across various tasks. However, their deployment in resource-constrained environments and concerns over user data privacy pose significant challenges. In contrast, Small Language Models (SLMs) offer computational efficiency but often lag in performance. To address these issues, we propose FedCoT, a federated framework designed for the Chain-of-Thought (CoT) distillation of knowledge from LLMs to SLMs, while ensuring the preservation of clients' data privacy. FedCoT ensures secure and efficient knowledge transfer from an LLM on a high-powered server to an SLM on a resource-constrained client, while adhering to privacy requirements. Leveraging perturbed prompts and rationales generated through the CoT approach, the framework enhances the performance of the client's SLM without compromising user data privacy within a multi-task learning framework. We propose two privacy protection strategies: the Exponential Mechanism Strategy and the Adaptive Exponential Mechanism Strategy, which balance user prompt privacy and the usability of rationales. Empirical evaluation on various text generation tasks demonstrates the effectiveness of FedCoT in training task-specific SLMs with enhanced performance while prioritizing data privacy protection. Our code has been contributed to the FATE open-source project and is now publicly accessible at \textit{https://github.com/FederatedAI/FATE-LLM/tree/main/python/fate_llm/algo/fedcot}
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。
