GuidaPA: Privacy-Preserving Chatbot for Public Administration via Federated Learning
Summary
GuidaPA is a privacy-preserving chatbot developed for the Italian Public Administration (PA), trained using Federated Learning (FL) on public documentation from SIGESON (8 pages) and SIDFORS (31 pages) platforms. This system is designed for future deployment with restricted internal data, avoiding central pooling due to regulatory and organizational constraints. GuidaPA incorporates role-based access control, secure client-side preprocessing, explicit monitoring of non-IID effects, and parameter-efficient federated fine-tuning via QLoRA (4-bit). Evaluated over 15 federated rounds with an 80/20 train-test split, the best federated model achieved ROUGE-1/2/L scores of 61.10/55.77/59.44, BLEU-4 of 45.02, and METEOR of 63.94. These results are comparable to private centralized fine-tuning, demonstrating FL's capability to deliver high-quality conversational AI for public services without centralizing sensitive data. Domain fine-tuning significantly improved ROUGE-1 from 41.45 to 62.18 and BLEU-4 from 26.97 to 50.90 compared to a general-purpose baseline.
Key takeaway
For AI Architects and ML Engineers deploying conversational AI in highly regulated sectors like public administration, GuidaPA demonstrates that Federated Learning is a robust solution. You can achieve high-quality chatbot performance comparable to centralized methods while strictly adhering to data privacy and localization requirements. Consider implementing FL with parameter-efficient fine-tuning for your next project involving sensitive, distributed data sources.
Key insights
Federated Learning enables high-quality, privacy-preserving chatbots for sensitive public administration data without centralizing information.
Principles
- Federated Learning maintains data locality for sensitive information.
- Domain-specific fine-tuning significantly boosts chatbot performance.
- Parameter-efficient methods like QLoRA are effective in FL setups.
Method
GuidaPA uses QLoRA (4-bit) for parameter-efficient federated fine-tuning over 15 rounds with an 80/20 train-test split per client, explicitly monitoring non-IID effects.
In practice
- Implement QLoRA (4-bit) for efficient federated LLM fine-tuning.
- Integrate role-based access control for secure chatbot interactions.
- Monitor non-IID data effects in federated learning deployments.
Topics
- Federated Learning
- Privacy-Preserving AI
- Chatbots
- Public Administration
- Large Language Models
- QLoRA
- Role-Based Access Control
Best for: NLP Engineer, CTO, VP of Engineering/Data, AI Engineer, Machine Learning Engineer, AI Architect
Related on AIssential
Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.