{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T20:34:36Z","timestamp":1761165276735,"version":"build-2065373602"},"reference-count":15,"publisher":"Sociedade Brasileira de Computa\u00e7\u00e3o - SBC","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>A identifica\u00e7\u00e3o de conluios em licita\u00e7\u00f5es p\u00fablicas \u00e9 um desafio persistente, com diversas abordagens baseadas em aprendizado de m\u00e1quina sendo exploradas na literatura. Este trabalho investiga a aplica\u00e7\u00e3o de Large Language Models (LLMs) na detec\u00e7\u00e3o de ind\u00edcios de conluio em licita\u00e7\u00f5es. Foram realizados testes utilizando t\u00e9cnicas de engenharia de prompt e fine-tuning, comparando o desempenho dos modelos com os de algoritmos tradicionais como Random Forest, Regress\u00e3o Log\u00edstica e Support Vector Machine. Os resultados demonstraram que, embora a engenharia de prompt n\u00e3o tenha alcan\u00e7ado resultados satisfat\u00f3rios, o fine-tuning permitiu que o ChatGPT 4o Mini superasse os algoritmos tradicionais nos conjuntos de dados analisados.<\/jats:p>","DOI":"10.5753\/sbbd.2025.247791","type":"proceedings-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T19:26:36Z","timestamp":1761074796000},"page":"893-899","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Models para detec\u00e7\u00e3o de conluios em licita\u00e7\u00f5es"],"prefix":"10.5753","author":[{"given":"Jorge N.","family":"Pav\u00e3o","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego","family":"Brand\u00e3o","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6257-2520","authenticated-orcid":false,"given":"Kele","family":"Belloze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"3742","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"Anisuzzaman, D., Malins, J. G., Friedman, P. A., and Attia, Z. I. (2025). Fine-tuning large language models for specialized use cases. Mayo Clinic Proceedings: Digital Health, 3(1):100184.","DOI":"10.1016\/j.mcpdig.2024.11.005"},{"key":"2","doi-asserted-by":"crossref","unstructured":"Benzinho, J. et al. (2024). Llm based chatbot for farm-to-fork blockchain traceability platform. Applied Sciences, 14(19).","DOI":"10.3390\/app14198856"},{"key":"3","unstructured":"Berryman, J. and Ziegler, A. (2024). Prompt Engineering for LLMs: The Art and Science of Building Large Language Model\u2013Based Applications. O\u2019Reilly Media, 1st edition."},{"key":"4","doi-asserted-by":"crossref","unstructured":"Huber, M. and Imhof, D. (2019). Machine learning with screens for detecting bid-rigging cartels. International Journal of Industrial Organization, 65:277\u2013301.","DOI":"10.1016\/j.ijindorg.2019.04.002"},{"key":"5","doi-asserted-by":"crossref","unstructured":"Huber, M., Imhof, D., and Ishii, R. (2022). Transnational machine learning with screens for flagging bid-rigging cartels. Journal of the Royal Statistical Society. Series A: Statistics in Society, 185:1074\u20131114.","DOI":"10.1111\/rssa.12811"},{"key":"6","doi-asserted-by":"crossref","unstructured":"Imhof, D. and Wallimann, H. (2021). Detecting bid-rigging coalitions in different countries and auction formats. International Review of Law and Economics, 68.","DOI":"10.1016\/j.irle.2021.106016"},{"key":"7","unstructured":"Lima, M. C. (2021). Deep vacuity: Detec\u00e7\u00e3o e classifica\u00e7\u00e3o autom\u00e1tica de padr\u00f5es com risco de conluio em dados p\u00fablicos de licita\u00e7\u00f5es de obras. Master\u2019s thesis, Universidade de Bras\u00edlia."},{"key":"8","doi-asserted-by":"crossref","unstructured":"OCDE (2021). Combate a cart\u00e9is em licita\u00e7\u00f5es no brasil: Uma revis\u00e3o das compras p\u00fablicas federais. Organiza\u00e7\u00e3o para a Coopera\u00e7\u00e3o e Desenvolvimento Econ\u00f4mico (OCDE).","DOI":"10.1787\/583501ec-pt"},{"key":"9","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez, M. G. et al. (2022). Collusion detection in public procurement auctions with machine learning algorithms. Automation in Construction, 133.","DOI":"10.1016\/j.autcon.2021.104047"},{"key":"10","doi-asserted-by":"crossref","unstructured":"Scoralick, L., Brand\u00e3o, D., and Belloze, K. (2024). Aprimoramento de modelos para detec\u00e7\u00e3o de conluios em licita\u00e7\u00f5es p\u00fablicas brasileiras com vari\u00e1veis estat\u00edsticas e modelos explic\u00e1veis. In Anais do XXXIX Simp\u00f3sio Brasileiro de Bancos de Dados, pages 680\u2013686, Porto Alegre, RS, Brasil. SBC.","DOI":"10.5753\/sbbd.2024.243170"},{"key":"11","doi-asserted-by":"crossref","unstructured":"Silveira, D. et al. (2022). Won\u2019t get fooled again: A supervised machine learning approach for screening gasoline cartels. Energy Economics, 105.","DOI":"10.1016\/j.eneco.2021.105711"},{"key":"12","doi-asserted-by":"crossref","unstructured":"Silveira, D. et al. (2023). Who are you? cartel detection using unlabeled data. International Journal of Industrial Organization, 88.","DOI":"10.1016\/j.ijindorg.2023.102931"},{"key":"13","unstructured":"Souza, R. V. F. D. (2023). Identifica\u00e7\u00e3o autom\u00e1tica de conluio em preg\u00f5es do comprasnet com aprendizado de m\u00e1quina. Master\u2019s thesis, Universidade de Bras\u00edlia."},{"key":"14","doi-asserted-by":"crossref","unstructured":"Velasco, R. et al. (2021). A decision support system for fraud detection in public procurement. International Transactions in Operational Research, 28:27\u201347.","DOI":"10.1111\/itor.12811"},{"key":"15","doi-asserted-by":"crossref","unstructured":"Wallimann, H., Imhof, D., and Huber, M. (2023). A machine learning approach for flagging incomplete bid-rigging cartels. Computational Economics, 62:1669\u20131720.","DOI":"10.1007\/s10614-022-10315-w"}],"event":{"name":"Simp\u00f3sio Brasileiro de Banco de Dados","number":"40","location":"Brasil","acronym":"SBBD 2025"},"container-title":["Anais do XL Simp\u00f3sio Brasileiro de Banco de Dados (SBBD 2025)"],"original-title":[],"link":[{"URL":"https:\/\/sol.sbc.org.br\/index.php\/sbbd\/article\/download\/37300\/37083","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/sol.sbc.org.br\/index.php\/sbbd\/article\/download\/37300\/37083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T19:27:15Z","timestamp":1761074835000},"score":1,"resource":{"primary":{"URL":"https:\/\/sol.sbc.org.br\/index.php\/sbbd\/article\/view\/37300"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":15,"URL":"https:\/\/doi.org\/10.5753\/sbbd.2025.247791","relation":{},"subject":[],"published":{"date-parts":[[2025,9,29]]}}}