Exploring Generative AI Techniques in Government: A Case Study

2025-04-06

AI Summary

To address the labor-intensive manual processes and low accessibility for non-technical users in governmental performance management, this study proposes a lightweight LLM-based intelligent agent architecture tailored for public-sector applications, instantiated as “Pubbie”—a domain-specific agent developed for Canada’s National Research Council (NRC). The architecture integrates domain knowledge injection, RoBERTa-based semantic embeddings, strategic fine-tuning, and few-shot learning to enable natural-language interaction and one-click document operations, ensuring domain fidelity while substantially reducing deployment overhead. Evaluated across 22 NRC pilot deployments, Pubbie achieved an average 68% reduction in performance data processing time and improved system usage efficiency among non-technical users by 3.2×. It marks the first end-to-end automation of governmental performance measurement, data management, and insight generation—demonstrating scalability, usability, and operational impact in real-world public administration contexts.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Application Domains: Humanities & Computational Social Science
• Humans and AI: Intelligent User Interfaces

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Search and Retrieval-Augmented AI: Agentic search

Abstract

The swift progress of Generative Artificial intelligence (GenAI), notably Large Language Models (LLMs), is reshaping the digital landscape. Recognizing this transformative potential, the National Research Council of Canada (NRC) launched a pilot initiative to explore the integration of GenAI techniques into its daily operation for performance excellence, where 22 projects were launched in May 2024. Within these projects, this paper presents the development of the intelligent agent Pubbie as a case study, targeting the automation of performance measurement, data management and insight reporting at the NRC. Cutting-edge techniques are explored, including LLM orchestration and semantic embedding via RoBERTa, while strategic fine-tuning and few-shot learning approaches are incorporated to infuse domain knowledge at an affordable cost. The user-friendly interface of Pubbie allows general government users to input queries in natural language and easily upload or download files with a simple button click, greatly reducing manual efforts and accessibility barriers.

Problem

• Exploring GenAI for government performance automation
• Developing intelligent agent Pubbie for data management
• Reducing manual efforts with user-friendly AI interface

Innovation

• LLM orchestration for intelligent agent development
• Semantic embedding via RoBERTa for data processing
• Few-shot learning to infuse domain knowledge affordably