contribuições para a recuperação da informação em documentos

Authors

DOI:

https://doi.org/10.33467/conci.v9i.24689

Keywords:

information retrieval, large language models, textual documents

Abstract

The production and sharing of information in multiple formats have grown exponentially in recent decades, intensifying challenges related to information organization, representation and retrieval. In this context, Large Language Models (LLMs) emerge as technologies capable of enhancing semantic search, interpreting natural language queries and generating contextualized responses, thereby expanding possibilities for information access. Thus, this study aimed to analyze, within the scientific literature, the use of LLMs in information retrieval from textual documents, identifying methodological approaches, application contexts, contributions, and limitations reported in the studies. Methodologically, a narrative literature review was conducted following a rigorous protocol, with searches carried out in the ACM Digital Library, ScienceDirect, Scopus and Web of Science databases. Articles published between 2020 and 2024, in Portuguese and English, available through open access were selected. After applying the inclusion and exclusion criteria and performing full-text reading, 12 publications composed the corpus of analysis. The studies were organized into four thematic axes: automation of document analysis in regulatory and institutional contexts; development of information retrieval methods and models; construction and enrichment of knowledge structures; and support for scientific research. It is concluded that LLMs enhance the interpretative capacity of information retrieval systems, although they still present limitations related to biases, hallucinations, computational costs and dependence on human supervision, requiring further research on transparency, performance evaluation and ethical and social impacts.

Downloads

Download data is not yet available.

Author Biographies

Daiane Campos Procópio, Federal University of Minas Gerais

Ph.D. candidate and Master’s degree (2025) in Knowledge Management and Organization from the Federal University of Minas Gerais (UFMG). She holds a bachelor’s degree in Library Science from UFMG (2013) and a bachelor’s degree in Systems Analysis and Development from the Pontifical Catholic University of Minas Gerais (2024).

Patrícia Nascimento Silva, Federal University of Minas Gerais

Adjunct Professor at the School of Information Science (ECI) at the Federal University of
Minas Gerais (UFMG). Professor and Researcher in the Graduate Program in Knowledge Management & Organization (PPGGOC) at ECI/UFMG. CNPq Productivity Fellow. Founder and leader of the research group: Open Data Observatory. Representative on the Management Committee of the National Open Data Infrastructure (CGINDA). Member of the Permanent Commission on Artificial Intelligence at UFMG. Ph.D. in Knowledge Management and Organization from the PPGGOC at ECI-UFMG; M.S. and B.S. in Information Systems.

Renato Rocha Souza, Federal University of Minas Gerais

He holds a Ph.D. in Information Science from the Federal University of Minas Gerais (2005) and completed postdoctoral research on “Semantic Technologies for Information Retrieval” at the University of South Wales, UK. He is a tenured faculty member in the graduate program at the School of Information Science at the Federal University of Minas Gerais (2010–) and a lecturer at the University of Vienna (2021–).

References

AMARATUNGA, Thimira. Understanding Large Language Models: learning their underlying concepts and technologies. Nugegoda: Apress, 2023.

BAEZA-YATES, Ricardo; RIBEIRO-NETO, Berthier. Recuperação de informação: conceitos e tecnologia das máquinas de busca. 2. ed. Porto Alegre: Bookman, 2013.

BARNETT, Scott et al. Seven Failure Points When Engineering a Retrieval Augmented Generation System. In: INTERNATIONAL CONFERENCE ON AI ENGINEERING – SOFTWARE ENGINEERING FOR AI, 3., 2024, Lisbon. Proceedings [...] Lisbon: ACM, 2024. p. 194-199. Disponível em: https://dl.acm.org/doi/10.1145/3644815.3644945. Acesso em: 1 ago. 2026.

BAWDEN, David; ROBINSON, Lyn. The dark side of information: overload, anxiety and other paradoxes and pathologies. Journal of Information Science, London, v. 35, n. 2, p. 180-191, 2008. Disponível em: https://journals.sagepub.com/doi/10.1177/0165551508095781. Acesso em: 1 ago. 2026.

BARRIUSO, Adrian Alónso et al. Recommendation system of scientific articles from discharge sumaries. Engineering Applications of Artificial Intelligence, London, v. 136, Part B, 109028, Oct. 2024. Disponível em: https://www.sciencedirect.com/science/article/pii/S0952197624011862. Acesso em: 1 ago. 2026.

BORKO, Harold. Information Science: what is it? American Documentation, [s.l.], p. 3-5, Jan. 1968. Disponível em: https://cmapspublic.ihmc.us/rid%3D1KR7TR64B-NMXB04-5SVP/BORKO(1968)-533107-Borko-H-v-19-n-1-p-35-1968.pdf. Acesso em: 31 jul. 2026.

BUSH, Vannevar. As We May Think. Atlantic Monthy, Washington, v. 176, n. 1, p. 101–108, Jul. 1945. Disponível em: https://www.theatlantic.com/magazine/archive/1945/07/as-wemay-think/303881/. Acesso em: 31 jul. 2026.

CARTA, Salvatore et al. A Zero-Shot Strategy for Knowledge Graph Engineering Using GPT-3.5. Procedia Computer Science, Netherlands, v. 246, Issue C, p. 2235–2243, 2024. Disponível em: https://www.sciencedirect.com/science/article/pii/S1877050924026231. Acesso em: 1 ago. 2026.

CAVALCANTE, Lívia Teixeira Canuto; OLIVEIRA, Adélia Augusta Souto de. Métodos de revisão bibliográfica nos estudos científicos. Psicologia em revista, Belo Horizonte, v. 26, n. 1, jan./abr. 2020. Disponível em: https://pepsic.bvsalud.org/scielo.php?script=sci_arttext&pid=S1677-11682020000100006. Acesso em: 1 ago. 2026.

CLOTHIAUX, Daniel; STARZL, Ravi. Extractive Search for Analysis of Biomedical Texts. In: INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 45., 2022. Madrid. Proceedings [...] Madrid: SIGIR, 2022. p. 3386 – 3387. Disponível em: https://dl.acm.org/doi/10.1145/3477495.3536328. Acesso em: 1 ago. 2026.

CONEGLIAN, Caio Saraiva; GONÇALVES, Paula Regina Ventura Amorim; SEGUNDO, José Eduardo Santarém. O profissional da informação na era do big data. Encontros Bibli: revista eletrônica de biblioteconomia e ciência da informação, Florianópolis, v. 22, n. 50, p. 128-143, set./dez., 2017. Disponível em: https://periodicos.ufsc.br/index.php/eb/article/view/1518-2924.2017v22n50p128. Acesso em: 1 ago. 2026.

DHAMANI, Numa; ENGLER, Maggie. Introduction to Generative AI. Shelter Island: Manning, 2024.

ISSON, Jean Paul; HARRIOTT, Jesse S. People Analytics in the Era of Big Data: Changing the Way You Attract, Acquire, Develop, and Retain Talent. Hoboken: Wiley, 2016.

JESUS, Ananda Fernanda de; ALGARVE, Wesley; SEGUNDO, José Eduardo Santarém. Dados sintéticos para treinamento de Inteligência Artificial: intersecções com a Organização e Representação da Informação e do Conhecimento. Advances on Knowledge Representation Journal, Belo Horizonte, v. 6, n. 1, 2026. Disponível em: https://periodicos.ufmg.br/index.php/advances-kr/article/view/64683. Acesso em: 1 ago. 2026.

KRUIPER, Ruben et al. A platform-based Natural Language processing-driven strategy for digitalising regulatory compliance processes for the built environment. Advanced Engineering Informatics, Netherlands, v. 62, Part B, 102653, p. 1-14, Oct. 2024. Disponível em: https://www.sciencedirect.com/science/article/pii/S147403462400301X. Acesso em: 1 ago. 2026.

MOOERS, Calvin Northrup. Zatocoding applied to mechanical organization of knowledge. American Documentation, [s. l.], v. 2, n. 1, p. 20-32, Jan. 1951. Disponível em: https://onlinelibrary.wiley.com/doi/abs/10.1002/asi.5090020107. Acesso em: 31 jul. 2026.

SILVA, Patrícia Nascimento. Recuperação de informação na Ciência da Informação: produção acadêmico-científica brasileira (2012-2021). Transinformação, Campinas, v. 35, e237336, 2023. Disponível em: https://periodicos.puc-campinas.edu.br/transinfo/article/view/7336. Acesso em: 1 ago. 2026.

OHR, Vebjørn; GUPTA, Dhruv. Scalable Range Search over Temporal and Numerical Expressions. In: ACM SIGIR INTERNATIONAL CONFERENCE ON THE THEORY OF INFORMATION RETRIEVAL, 2024, Washington, DC. Proceedings [...] Washington, DC: ACM, 2024. p. 91-100. Disponível em: https://dl.acm.org/doi/10.1145/3664190.3672509. Acesso em: 1 ago. 2026.

OLIVEIRA, Stênio Henrique et al. Infoxicação em tempos de infodemia: revisão integrativa. Brazilian Journal of Health Review, Curitiba, v. 4, n. 6, p. 25199-25211, nov./dec. 2021. Disponível em: https://ojs.brazilianjournals.com.br/ojs/index.php/BJHR/article/view/39660. Acesso em: 1 ago. 2026.

OZDEMIR, Sinan. Quick Start Guide to Large Language Models: Strategies and Best Practices for ChatGPT, Embeddings, Fine-Tuning, and Multimodal AI. 2nd ed. Hoboken: Pearson, 2025.

PROCÓPIO, Daiane Campos. Large Language Models para recuperação da informação em acervos históricos digitalizados. 2025. 154 f. Dissertação (Mestrado em Gestão e Organização do Conhecimento) – Escola de Ciência da Informação, Universidade Federal de Minas Gerais, Belo Horizonte, 2025. Disponível em: https://hdl.handle.net/1843/3339. Acesso em: 31 jul. 2026.

RAJA, Hina et al. Automated Category and Trend Analysis of Scientific Articles on Ophthalmology Using Large Language Models: Development and Usability Study. JMIR Formative Research, [s.l.], v. 8, e52462, p. 1-16, 2024. Disponível em: https://pubmed.ncbi.nlm.nih.gov/38517457/. Acesso em: 1 ago. 2026.

SARACEVIC, Tefko. Ciência da informação: origem, evolução e relações. Perspectivas em Ciência da Informação, Belo Horizonte, v. 1, n. 1, p. 41-62, jan./jun. 1996. Disponível em: https://periodicos.ufmg.br/index.php/pci/article/view/22308. Acesso em: 31 jul. 2026.

SAWARKAR, Kunal; MANGAL, Abhilasha; SOLANKI, Shivam Raj. Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers. In: INTERNATIONAL CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL, 7., 2024, San Jose. Proceedings [...] San Jose: IEEE, 2024. p. 155-161. Disponível em: https://ieeexplore.ieee.org/document/10707868. Acesso em: 1 ago. 2026.

SCHAEFFER, Marion. OLAF: An Ontology Learning Applied Framework. Procedia Computer Science, Netherlands, v. 225, p. 2106-2115, 2023. Disponível em: https://www.sciencedirect.com/science/article/pii/S1877050923013595?via%3Dihub. Acesso em: 1 ago. 2026.

SICILIANI, Lucia et al. AI-based decision support system for public procurement. Information Systems, Oxford, v. 119, 102284, p. 1-16, Oct. 2023. Disponível em: https://www.sciencedirect.com/science/article/pii/S0306437923001205. Acesso em: 1 ago. 2026.

STRATIS, Kyle. Whats is Generative AI? A Generative AI Primer for Business and Technical Leaders. Sebastopol: O’Reilly, 2024.

TOSLALI, Mert et al. AgraBOT: Accelerating Third-Party Security Risk Management in Enterprise Setting through Generative AI. In: ACM INTERNATIONAL CONFERENCE ON THE FOUNDATIONS OF SOFTWARE ENGINEERING, 32., 2024, Porto de Galinhas. Proceedings [...] Porto de Galinhas: ACM, 2024. p. 74-79. Disponível em: https://dl.acm.org/doi/10.1145/3663529.3663829. Acesso em: 1 ago. 2026.

WU, Leihong et al. A framework enabling LLMs into regulatory environment for transparency and trustworthiness and its application to drug labeling document. Regulatory Toxicology and Pharmacology, New York, v. 149, 105613, p. 1-9, May 2024. Disponível em: https://www.sciencedirect.com/science/article/pii/S0273230024000540. Acesso em: 1 ago. 2026.

Downloads

Published

2026-09-18

How to Cite

PROCÓPIO, Daiane Campos; SILVA, Patrícia Nascimento; SOUZA, Renato Rocha. contribuições para a recuperação da informação em documentos. ConCI: Convergências em Ciência da Informação, São Cristóvão, v. 9, p. e24689, 2026. DOI: 10.33467/conci.v9i.24689. Disponível em: https://periodicos.ufs.br/conci/article/view/24689. Acesso em: 19 sep. 2026.

Issue

Vol. 9 (2026)

Section

Artigo de revisão

License

Copyright (c) 2026 Daiane Campos Procópio, Patrícia Nascimento Silva, Renato Rocha Souza

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

ConCI adopts the CC BY 4.0 License , where licensees have the right to copy, distribute, display and perform the work and make derivative works from it, provided that due credit is given to the author or licensor.

ConCI considers that the author holds the copyright on his/her production, but the author must agree to grant the journal the right to the first publication. In addition, the author must agree that:
• in any publications in institutional repositories, book chapters or other productions resulting from works published in ConCI, due credit must be given to the initial publication.
• are authorized to publish and distribute their work online (eg, in institutional repositories or on their personal page) at any time before or during the editorial process, as this can generate productive changes as well as increase the impact and citation of the work published by ConCI.