mlsanityData to 14 Oct 2026

GuidaPA: Privacy-Preserving Chatbot for Public Administration via Federated Learning

arXiv 2606.01386 ↗First posted 31 May 2026cs.AI cs.CL cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

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

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 45 references that are in the map. First posted on arXiv 31 May 2026.

Builds on

18 of 45 references.

References · 18

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  6. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
  7. 2023Formalizing and Benchmarking Prompt Injection Attacks and Defensescited by 364
  8. 2024FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptationscited by 146
  9. 2024Data-efficient Fine-tuning for LLM-based Recommendationcited by 104
  10. 2024Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resourcescited by 93
  11. 2024RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMscited by 90
  12. 2024Federated Large Language Models: Current Progress and Future Directionscited by 27
6 more
  1. 2022IT5: Text-to-text Pretraining for Italian Language Understanding and Generationcited by 20
  2. 2023Benchmarking LLM powered Chatbots: Methods and Metricscited by 19
  3. 2024Unveiling LLM Evaluation Focused on Metrics: Challenges and Solutionscited by 18
  4. 2025FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Modelscited by 11
  5. 2024Addressing Hallucinations with RAG and NMISS in Italian Healthcare LLM Chatbotscited by 3
  6. 2023FedBot: Enhancing Privacy in Chatbots with Federated Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024FedCoT: Federated Chain-of-Thought Distillation for Large Language Models
  2. 2022FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning
  3. 2024Analysis of Privacy Leakage in Federated Large Language Models
  4. 2023Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
  5. 2024Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security
  6. 2024Privacy-Preserving Large Language Models: Mechanisms, Applications, and Future Directions
  7. 2026Federated Prompt Learning: A Unified Framework, Empirical Analysis, and Future Directions
  8. 2026From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning