GuidaPA: 通过联邦学习为公共行政提供隐私保护的聊天机器人
GuidaPA: Privacy-Preserving Chatbot for Public Administration via Federated Learning
AI总结：
提出GuidaPA，一个基于联邦学习（FL）在意大利公共行政文档上训练的隐私保护聊天机器人，通过参数高效的联邦微调（QLoRA）和角色访问控制，在保持数据本地化的同时实现了接近集中式微调的答案质量。
摘要：
我们提出了GuidaPA，一个为意大利公共行政（PA）设计的隐私保护聊天机器人，它通过联邦学习（FL）在两个国家PA平台SIGESON和SIDFORS的文档上进行训练。我们的语料库包括约8页的SIGESON手册和31页的SIDFORS手册/常见问题解答；虽然本研究使用公开文档作为安全代理，但预期的部署将扩展到受限制的内部来源（例如，工单、官员手册、数据库提取），这些数据由于监管和组织约束无法集中汇集。GuidaPA集成了基于角色的访问控制、安全的客户端预处理、对非独立同分布效应的显式监控以及大语言模型的参数高效联邦微调。使用QLoRA（4位）进行15轮联邦训练，每个客户端采用80/20的训练-测试划分，我们使用ROUGE、BLEU-4和METEOR评估答案质量。最佳联邦模型达到了ROUGE-1/2/L分别为61.10/55.77/59.44，BLEU-4为45.02，METEOR为63.94——接近私有集中式微调的性能，同时保持数据在本地。与通用基线相比，领域微调将ROUGE-1从41.45提高到62.18，BLEU-4从26.97提高到50.90。总体而言，结果表明FL可以在不进行集中数据共享的情况下，为公共服务提供高质量的对话式AI。
英文摘要：
We present GuidaPA, a privacy-preserving chatbot for the Italian Public Administration (PA) trained via Federated Learning (FL) on documentation from two national PA platforms, SIGESON and SIDFORS. Our corpus includes approximately 8 pages of SIGESON manuals and 31 pages of SIDFORS manuals/FAQs; while this study uses public documentation as a safe proxy, the intended deployment extends to restricted internal sources (e.g., tickets, officer manuals, database extracts) that can not be centrally pooled due to regulatory and organizational constraints. GuidaPA integrates role-based access control, secure client-side preprocessing, explicit monitoring of non-IID effects, and parameter-efficient federated fine-tuning of large language models. Using QLoRA (4-bit) over 15 federated rounds with an 80/20 train-test split per client, we evaluate answer quality with ROUGE, BLEU-4, and METEOR. The best federated model achieves ROUGE-1/2/L of 61.10/55.77/59.44, BLEU-4 of 45.02, and METEOR of 63.94-close to private centralized fine-tuning while keeping data on-site. Compared to the general-purpose baseline, domain fine-tuning improves ROUGE-1 from 41.45 to 62.18 and BLEU-4 from 26.97 to 50.90. Overall, the results indicate that FL can deliver high-quality conversational AI for public services without centralized data sharing
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。
