Sélection de la langue

Gouvernement du Canada / Government of Canada

Recherche

Exploring generative artificial intelligence techniques in government: a case study

Par Conseil national de recherches du Canada

DOITrouver le DOI : https://doi.org/10.1109/MIS.2025.3569429
AuteurRechercher : Identifiant ORCID : https://orcid.org/0009-0006-4861-0432; Rechercher : 1Identifiant ORCID : https://orcid.org/0000-0002-7886-439X; Rechercher : 2Identifiant ORCID : https://orcid.org/0009-0006-3193-3737
Affiliation
  1. Conseil national de recherches Canada. Technologies numériques
  2. Conseil national de recherches Canada. Bureau de la vérification et de l'évaluation
FormatTexte, Article
Sujetdatabases; intelligent agents; government; semantics; manuals; few shot learning; encoding; bidirectional control; performance evaluation; generative ai; artificial intelligence; large language models; project management
Résumé
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 article 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.
Date de publication
Maison d’éditionIEEE
Dans
  • IEEE Intelligent Systems 40, nº 4 (14 juillet 2025) : 37–45.
Langueanglais
Publications évaluées par des pairsOui
Exporter la noticeExporter en format RIS
Signaler une correctionSignaler une correction (s'ouvre dans un nouvel onglet)
Identificateur de l’enregistrement6e00a357-3203-4e65-ada5-c163dff6a1df
Enregistrement créé2025-09-18
Enregistrement modifié2025-09-19
Date de modification :