Organização e Arquitetura da Informação em Large Language Models:  interseções na Ciência da Informação

Daiane Campos Procópio; Patrícia Nascimento Silva

doi:10.5433/1981-8920.2026v31n1p149

Authors

Daiane Campos Procópio Federal University of Minas Gerais https://orcid.org/0000-0002-9006-191X
Patrícia Nascimento Silva Federal University of Minas Gerais https://orcid.org/0000-0002-2405-8536

DOI:

https://doi.org/10.5433/1981-8920.2026v31n1p149

Keywords:

Information Architecture, Large Language Models, Literature review

Abstract

Objective: To identify and analyze the organization and information architecture in Large Language Models (LLMs), relating them to Artificial Intelligence (AI) techniques and discussing these findings within the context of Information Science (IS).
Methodology: this bibliographic research consists of a literature review adopting a mixed-methods approach. A rigorous protocol was applied to investigate the topic in the ACM Digital Library, ScienceDirect, Scopus and Web of Science databases between June and August 2025. Data were analyzed both quantitatively and qualitatively through content analysis, following Bardin’s framework, particularly through categorical analysis.
Results: a total of 53 studies published between 2022 and 2025, from 26 countries, were examined, leading to the identification of 16 categories of AI techniques applied to LLMs. These techniques were related to the four Information Architecture systems proposed by Rosenfeld, Morville, and Arango: organization, labeling, navigation, and search, demonstrating contributions to the development and application of LLMs across different domains.
Conclusions: this research contributes by highlighting how information organization and architecture interact with artificial intelligence and traditional tools in the field, such as metadata, thesauri, and taxonomies, which can be applied to understand how LLMs organize, represent, and make data available. Furthermore, it provides an important conceptual foundation, supporting new studies and solutions involving data curation and the training of these systems. The study also reinforces the relevance of information science fundamentals in the analysis of emerging technologies.

Downloads

Download data is not yet available.

Author Biographies

Daiane Campos Procópio, Federal University of Minas Gerais

Master's degree in Knowledge Management and Organization from the Postgraduate Program (PPGGOC) at the Universidade Federal de Minas Gerais (UFMG). Belo Horizonte, Brasil.

Patrícia Nascimento Silva, Federal University of Minas Gerais

PhD in Knowledge Management and Organization from the Universidade Federal de Minas Gerais (UFMG). Professor at the Escola de Ciência da Informação (ECI) and the Universidade Federal de Minas Gerais and in the Postgraduate Program in Knowledge Management and Organization (PPGGOC). Belo Horizonte, Brasil.

References

ADESEYE, A.; ISOAHO, J.; MOHAMMAD, T. LLM-assisted qualitative data analysis: security and privacy concerns in gamified workforce studies. Procedia Computer Science, [S.l.], v. 257, p. 60-67, 2025. DOI: 10.1016/j.procs.2025.03.011.

AGBAREIA, R. et al. Visual-textual integration in LLMs for medical diagnosis: a preliminary quantitative analysis. Computational and Structural Biotechnology Journal, [S.l.], v. 27, p. 184-189, 2025. DOI: 10.1016/j.csbj.2024.12.019.

ALAMMAR, J.; GROOENDORST, M. Hands-On Large Language Models. Sebastopol: O’Reilly, 2024.

ALGHAMDI, H.; MOSTAFA, A. Advancing EHR analysis: Predictive medication modeling using LLMs. Information Systems, [S.l.], v. 131, 102528, 2025. DOI: 10.1016/j.is.2025.102528

ARAÚJO, C. A. A. O que é Ciência da Informação? Belo Horizonte: KMA, 2018. Disponível em: https://teste.eci.ufmg.br/wp-content/uploads/2024/03/O-QUE-E-CIENCIA-DA-INFORMACAO.pdf. Acesso em: 28 ago. 2025.

BADALOTTI, D. et al. Development of a natural language processing (NLP) model to automatically extract clinical data from electronic health records: results from an Italian comprehensive stroke center. International Journal of Medical Informatics, [S.l.], v. 192, 105626, 2024. DOI: 10.1016/j.ijmedinf.2024.105626.

BARDIN, L. Análise de conteúdo. São Paulo: Edições 70, 2016.

CHEN, K. et al. A Survey on Privacy Risks and Protection in Large Language Models. arXiv:2505.01976v1, 2025. DOI: 10.48550/arXiv.2505.01976.

CHEN, K. et al. LLM-assisted multi-teacher continual learning for visual question answering in robotic surgery. arXiv:2402.16664v3, 2024. DOI: 10.48550/arXiv.2402.16664.

CHEN, L. et al. Application of retrieval-augmented generation for interactive industrial knowledge management via a large language model. Computer Standards & Interfaces, [S.l.], v. 94, 103995, 2025. DOI: 1016/j.csi.2025.103995.

CHO, H. et al. Extracting lung cancer staging descriptors from pathology reports: a generative language model approach. Journal of Biomedical Informatics, [S.l.], v. 157, 104720, 2024. DOI: 10.1016/j.jbi.2024.104720.

CHO, N. et al. FISHNET: financial intelligence from sub-querying, harmonizing, neural-conditioning, expert swarms, and task planning. In: ACM International Conference on AI in Finance (ICAIF ’24), 5., 2024, Brooklyn. Proceedings [...]. [S.l.]: ACM, 2024. p. 1-9. DOI:1145/3677052.3698597.

CHOI, H.; JEONG, J. A Conceptual Framework for a Latest Information-Maintaining Method Using Retrieval-Augmented Generation and a Large Language Model in Smart Manufacturing: Theoretical Approach and Performance Analysis. Machines, Basel, v. 13, n. 94, 2025a. DOI: 10.3390/machines13020094.

CHOI, H.; JEONG, J. Domain-specific manufacturing analytics framework: an integrated architecture with retrieval-augmented generation and Ollama-based models for manufacturing execution systems environments. Processes, [S.l.], v. 13, n. 670, 2025b. DOI: 10.3390/pr13030670

CHOW, A. R. ChatGPT May Be Eroding Critical Thinking Skills, According to a New MIT Study. Time, 23 jun. 2025. Disponível em: https://time.com/7295195/ai-chatgpt-google-learning-school/. Acesso em: 30 jul. 2025.

CORRÊA, L. N. Metodologia científica: Para trabalhos acadêmicos e artigos. Florianopolis: Do Autor, 2008.

COSTA, D. G. et al. A method to promote safe cycling powered by large language models and AI agents. MethodsX, [S.l.], v. 13, 102880, 2024. DOI: 10.1016/j.mex.2024.102880.

CRESWELL, J. W.; CRESWELL, J. D. Projeto de pesquisa: métodos qualitativo, quantitativo e misto. 5. ed. Porto Alegre: Penso, 2021.

DHAMANI, N.; ENGLER, M. Introduction to Generative AI. Shelter Island: Manning, 2024.

ELAHI, A.; TAGHVAEI, F. Combining financial data and news articles for stock price movement prediction using large language models. arXiv:2411.01368v1, 2024. DOI: 10.48550/arXiv.2411.01368.

FERREIRA, S. A; OLIVEIRA, D. A. Desinformação, crise de confiança na ciência e necessidade de políticas para divulgação científica. Ciência da Informação Express, v. 2, n. 4, p. 1-6, 9 abr. 2021. DOI: 10.60144/v2i.2021.28.

FU, X. et al. Deciphering public voices in the digital era: benchmarking ChatGPT for analyzing citizen feedback in Hamilton, New Zealand. Journal of the American Planning Association, [S.l.], v. 90, n. 4, p. 728-741, 2024. DOI: 10.1080/01944363.2024.2309259.

GABRIEL-PETIT, P. Designing Information Architecture: A practical guide to structuring digital content for findability and easy navigability. Birmingham: Packt Publishing, 2025.

HAN, B.; SUSNJAK, T.; MATHRANI, A. Automating systematic literature reviews with retrieval-augmented generation: A comprehensive overview. Applied Sciences, [S.l.], v. 14, n. 9103, 2024. DOI: 10.3390/app14199103.

JAIMOVITCH-LÓPEZ, G. et al. Can language models automate data wrangling? Machine Learning, [S.l.], v. 112, p. 2053-2082, 2022. DOI: 10.1007/s10994-022-06259-9.

JEONG, Y. et al. Advancing tinnitus therapeutics: GPT-2 driven clustering analysis of cognitive behavioral therapy sessions and Google T5-based predictive modeling for THI score assessment. IEEE Access, [s.l.], v. 12, p. 52414-52429, 2024. DOI: 10.1109/ACCESS.2024.3383020.

KALLENS, P. C.; KRISTENSEN-MCLACHLAN, R. D.; CHRISTIANSEN, M. H. Large Language Models Demonstrate the Potential of Statistical Learning in Language. Cognitive Science, [S.l.], v. 47, n. 3, 2023. DOI: 10.1111/cogs.13256.

LI, H. et al., A review on enhancing agricultural intelligence with large language models. Artificial Intelligence in Agriculture, [S. l.], v. 15, p. 671-685, 2025. DOI: 10.1016/j.aiia.2025.05.006.

LI, Y. et al. Deep learning and methods based on large language models applied to stellar light curve classification. Intelligent Computing, [s.l.], v. 4, 0110, 2025. DOI: 10.34133/icomputing.0110.

LIU, F. et al. Aggregated knowledge model: Enhancing domain-specific QA with fine-tuned and retrieval-augmented generation models. In: INTERNATIONAL CONFERENCE ON AI-ML SYSTEMS, 4., 2024, Baton Rouge. Proceedings [...]. New York: ACM, 2024. p. 1-7. DOI: 10.1145/3703412.3703434.

LIU, J. et al. Fisher information-based efficient curriculum federated learning with large language models. arXiv:2410.00131v2, 2024. DOI: 10.48550/arXiv.2410.00131.

LIU, X. et al. Military equipment entity extraction based on large language model. Applied Sciences, [s.l.], v. 14, n. 9063, 2024. DOI: 10.3390/app14199063.

LIMA, G. A. B. O. Arquitetura da Informação. In: Miranda, R. C. R. Arquitetura da informação na Câmara dos Deputados. Brasília: Câmara dos Deputados, 2016. Cap. 2, p. 45-63.

LUKICHEV, M. Understanding data quality’s impact on Large Language Models. Medium, 18 jul. 2024. Disponível em: https://medium.com/telmai1/understanding-data-qualitys-impact-on-large-language-models-01e9e54a5017. Acesso em: 30 jul. 2025.

NASCIMENTO SILVA, P. Recuperação de Informação na Ciência da Informação: produção acadêmico-científica brasileira (2012-2021). Transinformação, Campinas, v. 35, p. 1–17, 2023. Disponível em: https://periodicos.puc-campinas.edu.br/transinfo/article/view/7336. Acesso em: 19 fev. 2026.

MACIE, G. C.; NASCIMENTO, N. M.; MADIO, T. C. C. Arquitetura e recuperação da informação: uma abordagem do Sistema Integrado de Gestão Acadêmica (SIGA) da Universidade Eduardo Mondlane. Em Questão, Porto Alegre, v. 30, e-139451, 2024. DOI: 10.1590/1808-5245.30.139451.

MATIAS-PEREIRA, J. Manual de metodologia da pesquisa científica. 4. ed. São Paulo: Atlas, 2019.

MEMDUHOĞLU, A.; FULMAN, N.; ZIPF, A. Enriching building function classification using large language model embeddings of OpenStreetMap Tags. Earth Science Informatics, [S.l.], v. 17, p. 5403-5418, 2024. DOI: 10.1007/s12145-024-01463-8.

MISHRA, M. et al. DataAgent: evaluating large language models’ ability to answer zero-shot, natural language queries. arXiv:2404.00188v1, 2024. DOI: 10.48550/arXiv.2404.00188.

MOHAMMAD, R.; ALKHNBASHI, O. S.; HAMMOUDEH, M. Optimizing large language models for Arabic healthcare communication: a focus on patient-centered NLP applications. Big Data and Cognitive Computing, [S.l.], v. 8, n. 157, 2024. DOI: 10.3390/bdcc8110157.

NOELS, S; DE BLAERE, J; DE BIE, T. A Dutch Financial Large Language Model. In: ACM INTERNATIONAL CONFERENCE ON AI IN FINANCE, 5., 2024, Brooklyn, NY. Proceedings [...]. New York: ACM, 2024. p. 1-9. DOI: 10.1145/3677052.3698628.

PAPAGEORGIOU, G. et al. Enhancing e-government services through state-of-the-art, modular, and reproducible architecture over large language models. Applied Sciences, [S.l.], v. 14, n. 8259, 2024. DOI: 10.3390/app14188259.

PAIS, C. et al. Large language models for preventing medication direction errors in online pharmacies. Nature Medicine, [s.l.], v. 30, n. 6, p. 1574-1582, 2024. DOI: 10.1038/s41591-024-02933-8.

PRAGYAN, K. C. et al. Toward regulatory compliance: a few-shot learning approach to extract processing activities. In: IEEE International Requirements Engineering Conference Workshops, 32., 2024. Proceedings [...]. [S.l.]: IEEE, 2024. p. 241-248. DOI: 10.1109/REW61692.2024.00038.

RANGAN, K.; YIN, Y. A fine-tuning enhanced RAG system with quantized influence measure as AI judge. Scientific Reports, [S. l.], v. 14, n. 27446, 2024. DOI: 10.1038/s41598-024-79110-x.

REDDY, V. et al. DocFinQA: a long-context financial reasoning dataset. arXiv:2401.06915v2, 2024. DOI: 10.48550/arXiv.2401.06915.

REN, Y. et al. WaterGPT: training a large language model to become a hydrology expert. Water, [S.l.], v. 16, n. 3075, 2024. DOI: 10.3390/w16213075.

ROSENFELD, L.; MORVILLE, P.; ARANGO, J. Information Architecture. 4th. ed. Sebastopol: O’Reilly, 2015.

SADICK, A. M.; CHINAZZO, G. What did the occupant say? Fine-tuning and evaluating a large language model for efficient analysis of multi-domain indoor environmental quality feedback. Building and Environment, [S.l.], v. 274, 112735, 2025. DOI: 10.1016/j.buildenv.2025.112735.

SARZAEIM, P.; MAHMOUD, Q. H.; AZIM, A. A Framework for LLM-Assisted Smart Policing System. IEEE Access, [S.l.], v. 12, p. 74915-74929, 2024. DOI: 10.1109/ACCESS.2024.3404862.

SONG, Z. et al. A scientific-article key-insight extraction system based on multi-actor of fine-tuned open-source large language models. Scientific Reports, [s. l.], v. 15, n. 1608, 2025. DOI: 10.1038/s41598-025-85715-7.

STANLEY, J. et al. Large language models deconstruct the clinical intuition behind diagnosing autism. Cell, [S.l.], v. 188, p. 2235-2248, 2025. DOI: 10.1016/j.cell.2025.02.025.

SUNG, C.; LEE, Y.; TSAI, Y. A New Pipeline for Generating Instruction Dataset via RAG and Self Fine-Tuning. In: IEEE ANNUAL COMPUTERS, SOFTWARE, AND APPLICATIONS CONFERENCE, 48., 2024. Proceedings [...]. [S.l.]: IEEE, 2024. DOI: 10.1109/COMPSAC61105.2024.00371.

TANABE, K. et al. Enhancing financial domain adaptation of language models via model augmentation. arXiv:2411.09249v1, 2024. DOI: 10.48550/arXiv.2411.09249.

TANABE, K. et al. JaFIn: Japanese financial instruction dataset. In: IEEE Symposium on Computational Intelligence for Financial Engineering and Economics, 2024. Proceedings [...]. [S.l.]: IEEE, 2024. p. 1-8. DOI: 10.1109/CIFEr62890.2024.10772973.

TAYLOR, N. et al. Model development for bespoke large language models for digital triage assistance in mental health care. Artificial Intelligence in Medicine, [S.l.], v. 157, 102988, 2024. DOI: 10.1016/j.artmed.2024.102988.

TOJIMA, T.; YOSHIDA, M. Zero-shot classification of art with large language models. IEEE Access, [S.l.], v. 13, p. 17426-17435, 2025. DOI: 10.1109/ACCESS.2025.3532995.

TONG, X. et al. LEGF-DST: LLMs-enhanced graph-fusion dual-stream transformer for fine-grained Chinese malicious SMS detection. Computers, Materials & Continua (CMC), [S.l.], v. 82, n. 2, p. 1902-1919, 2025. DOI: 10.32604/cmc.2024.059018.

TORINO, E. et al. A relação entre a arquitetura da informação e experiência do usuário sob a ótica dos pesquisadores da Ciência da Informação brasileira. Biblos: Revista do Instituto de Ciências Humanas e da Informação, Rio Grande, v. 36, n. 1, p. 219-237, 2022. DOI: 10.14295/biblos.v36i1.13769.

VALLE, P. R. D.; FERREIRA, J. L. Análise de conteúdo na perspectiva de Bardin: contribuições e limitações para a pesquisa qualitativa em Educação. Educação em Revista, Belo Horizonte, v. 41, e49377, 2025. DOI: http://dx.doi.org/10.1590/0102-469849377.

WANG, H. et al. DRG-LLaMA: tuning LLaMA model to predict diagnosis-related group for hospitalized patients. npj Digital Medicine, [S.l.], v. 7, n. 16, 2024. DOI: 10.1038/s41746-023-00989-3.

WANG, T. et al. A Multimodal Large Language Model Framework for Intelligent Perception and Decision-Making in Smart Manufacturing. Sensors, Basel, v. 25, n. 3072, 2025. Disponível em: https://www.mdpi.com/1424-8220/25/10/3072. Acesso em: 26 ago. 2025.

WEI, W. R.; HUANG, L.; WANG, J. J. Retrieval-Augmented Generation for LLM Applications: transforming search, recommendation, and AI assistants. Sebastopol, CA: O’Reilly, 2025.

WIEST, I. C. et al. Privacy-preserving large language models for structured medical information retrieval. NPJ Digital Medicine, [S.l.], v. 7, n. 257, 2024. DOI: 10.1038/s41746-024-01233-2.

WU, L. et al. A framework enabling LLMs into regulatory environment for transparency and trustworthiness and its application to drug labeling document. Regulatory Toxicology and Pharmacology, [s l.], v. 149, 105613, 2024. DOI: 10.1016/j.yrtph.2024.105613.

YAN, H.; SHAO, D. Multimodal medical image analysis: integrating LLM and RAG deep learning strategies. Journal of Advances in Information Technology, [S.l.], v. 16, n. 4, p. 568-581, 2025. DOI: 10.12720/jait.16.4.568-581.

YANG, J. et al. RDguru: a conversational intelligent agent for rare diseases. IEEE Journal of Biomedical and Health Informatics, [S.l.], p. 1-12, 2024. DOI: 10.1109/JBHI.2024.3464555.

ZHAO, X. et al. Research on fine-tuning optimization strategies for large language models in tabular data processing. Biomimetics, [S.l.], v. 9, n. 708, 2024. DOI: 10.3390/biomimetics9110708.

ZHANG, K. et al. Batch-ICL: Effective, efficient, and order-agnostic in-context learning. arXiv:2401.06469v3, 2024. DOI: 10.48550/arXiv.2401.06469.

ZHENG, J.; WANG, H.; YAO, J. Building lightweight domain-specific consultation systems via inter-external knowledge fusion contrastive learning. IEEE Access, [S.l.], v. 12, p. 113244-113259, 2024. DOI: 10.1109/ACCESS.2024.3434648.

ZHOU, B.; GEIßLER, D.; LUKOWICZ, P. Misinforming LLMs: vulnerabilities, challenges and opportunities. arXiv:2408.01168v1, Aug. 2024. DOI: 10.48550/arXiv.2408.01168.

ZHOU, S. et al. A user-centered framework for data privacy protection using large language models and attention mechanisms. Applied Sciences, [s.l.], v. 14, n. 6824, 2024. DOI: 10.3390/app14156824.

ZHU, F. et al. TAT-LLM: a specialized language model for discrete reasoning over financial tabular and textual data. In: ACM International Conference on AI in Finance, 5., 2024, Brooklyn. Proceedings [...]. Brooklyn: ACM, 2024. p. 1-9. DOI: 10.1145/3677052.3698685.

ZHU, G. et al. CMLLM: A novel cross-modal large language model for wind power forecasting. Energy Conversion and Management, [S.l.], v. 330, 119673, 2025. DOI: 10.1016/j.enconman.2025.119673.