Bridging Citizens and Public Services: Improving Service Association with Retrieval-Augmented Generation (RAG) Labels

Ticiana L. Coelho da Silva, Celso França, Marcos André Gonçalves, Leonardo Rocha, Leonardo Alamy, Fernando Sola Pereira, Eduardo Soares de Paiva


Abstract
Linking citizen complaints to the public services they concern remains a major challenge in the Brazilian federal administration. In 2025, over 1.2 million manifestations were submitted across 328 agencies, yet only about 1.8% are currently associated with a specific service, limiting large-scale monitoring and evidence-based management. We cast this task as an extreme multi-class text classification problem marked by severe class imbalance and strong lexical–semantic gaps between citizen language and official service descriptions. Building on recent work that reframes the task as information retrieval, we combine sparse retrieval with BM25 over representative complaint corpora and dense retrieval enriched with RAG-labels: semantically expanded label descriptions generated via Retrieval-Augmented Generation and Small Language Models. This approach markedly reduces vocabulary mismatch and semantic ambiguity, yielding substantial gains over direct text or embedding matching. To our knowledge, this is the first Portuguese-language application of RAG-labels for service–complaint association. In real operational data from the Federal Ombudsman Office, our method can automatically assign plausible services to roughly 73% of previously unlabeled cases, improving coverage and supporting more effective public service evaluation.
Anthology ID:
2026.propor-1.13
Volume:
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
Month:
April
Year:
2026
Address:
Salvador, Brazil
Editors:
Marlo Souza, Iria de-Dios-Flores, Diana Santos, Larissa Freitas, Jackson Wilke da Cruz Souza, Eugénio Ribeiro
Venue:
PROPOR
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
131–140
Language:
URL:
https://aclanthology.org/2026.propor-1.13/
DOI:
Bibkey:
Cite (ACL):
Ticiana L. Coelho da Silva, Celso França, Marcos André Gonçalves, Leonardo Rocha, Leonardo Alamy, Fernando Sola Pereira, and Eduardo Soares de Paiva. 2026. Bridging Citizens and Public Services: Improving Service Association with Retrieval-Augmented Generation (RAG) Labels. In Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1, pages 131–140, Salvador, Brazil. Association for Computational Linguistics.
Cite (Informal):
Bridging Citizens and Public Services: Improving Service Association with Retrieval-Augmented Generation (RAG) Labels (Silva et al., PROPOR 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.propor-1.13.pdf