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

翻译：我们提出GuidaPA，一种为意大利公共行政（PA）设计的隐私保护聊天机器人，它通过联邦学习（FL）在SIGESON和SIDFORS这两个国家级PA平台的文档上训练而成。我们的语料包含约8页SIGESON手册和31页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，但预期部署将扩展到因监管和组织限制而无法集中汇总的受限内部资料（如工单、官员手册、数据库提取内容）。GuidaPA集成了基于角色的访问控制、安全的客户端预处理、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。采用QLoRA（4比特）在15轮联邦训练中，每个客户端按80/20划分训练测试集，我们使用ROUGE、BLEU-4和METEOR评估答案质量。最优联邦模型的ROUGE-1/2/L得分分别为61.10/55.77/59.44，BLEU-4得分为45.02，METEOR得分为63.94，接近私有集中微调的性能，同时数据保留在本地。与通用基线相比，领域微调将ROUGE-1从41.45提升至62.18，BLEU-4从26.97提升至50.90。总体结果表明，FL可以在无需集中数据共享的情况下，为公共服务提供高质量的对话式人工智能。