{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T20:35:35Z","timestamp":1761165335730,"version":"build-2065373602"},"reference-count":20,"publisher":"Sociedade Brasileira de Computa\u00e7\u00e3o - SBC","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Embora grandes modelos de linguagem obtenham bons resultados na tarefa de Text-to-SQL, o alto custo computacional limita a ado\u00e7\u00e3o dos mesmos. Este estudo avalia a viabilidade de pequenos modelos como alternativa, analisando a rela\u00e7\u00e3o entre tamanho e desempenho, utilizando o modelo Qwen2.5 nas variantes de 0.5B a 32B de par\u00e2metros. Experimentos foram realizados no benchmark Spider e em um banco de dados com informa\u00e7\u00f5es de empresas brasileiras, com o objetivo de analisar a efic\u00e1cia da abordagem em um contexto de aplica\u00e7\u00e3o real. Os resultados indicam que o modelo de 3B oferece o melhor equil\u00edbrio entre custo e desempenho, enquanto os de 14B e 32B, embora mais caros, apresentam desempenho superior.<\/jats:p>","DOI":"10.5753\/sbbd.2025.247042","type":"proceedings-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T19:26:36Z","timestamp":1761074796000},"page":"140-153","source":"Crossref","is-referenced-by-count":0,"title":["Leis de Escala para Text-to-SQL: Um Estudo sobre a Rela\u00e7\u00e3o entre Tamanho e Desempenho de Modelos de Linguagem"],"prefix":"10.5753","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6304-4978","authenticated-orcid":false,"given":"Let\u00edcia O.","family":"Silva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4200-9650","authenticated-orcid":false,"given":"Paulo H. C.","family":"Silva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0713-0583","authenticated-orcid":false,"given":"Fabr\u00edcio A.","family":"Silva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"3742","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"1","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., and Zettlemoyer, L. (2023). QLoRA: Efficient Finetuning of Quantized LLMs. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023."},{"key":"2","unstructured":"Dong, X., Zhang, C., Ge, Y., Mao, Y., Gao, Y., Chen, L., Lin, J., and Lou, D. (2023). C3: Zero-shot Text-to-SQL with ChatGPT. ArXiv, abs\/2307.07306."},{"key":"3","doi-asserted-by":"crossref","unstructured":"Gao, D., Wang, H., Li, Y., Sun, X., Qian, Y., Ding, B., and Zhou, J. (2024). Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation. Proc. VLDB Endow.","DOI":"10.14778\/3641204.3641221"},{"key":"4","doi-asserted-by":"crossref","unstructured":"Hong, Z., Yuan, Z., Zhang, Q., Chen, H., Dong, J., Huang, F., and Huang, X. (2024). Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL. ArXiv, abs\/2406.08426.","DOI":"10.1109\/TKDE.2025.3609486"},{"key":"5","unstructured":"Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2022). LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR 2022."},{"key":"6","doi-asserted-by":"crossref","unstructured":"Jos\u00e9, M. and Cozman, F. (2021). mRAT-SQL+GAP: A Portuguese Text-to-SQL Transformer. In Anais da X Brazilian Conference on Intelligent Systems, BRACIS 2021.","DOI":"10.1007\/978-3-030-91699-2_35"},{"key":"7","doi-asserted-by":"crossref","unstructured":"Li, H., Zhang, J., Liu, H., Fan, J., Zhang, X., Zhu, J., Wei, R., Pan, H., Li, C., and Chen, H. (2024a). CodeS: Towards Building Open-source Language Models for Text-to-SQL. Proc. ACM Manag. Data.","DOI":"10.1145\/3654930"},{"key":"8","unstructured":"Li, Z., Wang, X., Zhao, J., Yang, S., Du, G., Hu, X., Zhang, B., Ye, Y., Li, Z., Zhao, R., and Mao, H. (2024b). PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency. ArXiv, abs\/2403.09732."},{"key":"9","unstructured":"Liu, X., Shen, S., Li, B., Ma, P., Jiang, R., Zhang, Y., Fan, J., Li, G., Tang, N., and Luo, Y. (2024). A Survey of NL2SQL with Large Language Models: Where are we, and where are we going? ArXiv, abs\/2408.05109."},{"key":"10","doi-asserted-by":"crossref","unstructured":"Miranda, B. and Campelo, C. E. C. (2024). How effective is an LLM-based Data Analysis Automation Tool? A Case Study with ChatGPT\u2019s Data Analyst. In Anais do XXXIX Simp\u00f3sio Brasileiro de Bancos de Dados, SBBD 2024.","DOI":"10.5753\/sbbd.2024.240841"},{"key":"11","unstructured":"Mohammadjafari, A., Maida, A. S., and Gottumukkala, R. (2024). From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems. ArXiv, abs\/2410.01066."},{"key":"12","doi-asserted-by":"crossref","unstructured":"Oliveira, A., Nascimento, E., Pinheiro, J. a., Avila, C. V. S., Coelho, G., Feij\u00f3, L., Izquierdo, Y., Garc\u00eda, G., Leme, L. A. P. P., Lemos, M., and Casanova, M. A. (2024). Small, Medium, and Large Language Models for Text-to-SQL. In Conceptual Modeling: 43rd International Conference, ER 2024.","DOI":"10.1007\/978-3-031-75872-0_15"},{"key":"13","doi-asserted-by":"crossref","unstructured":"Pourreza, M. and Rafiei, D. (2024). DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models. In Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024.","DOI":"10.18653\/v1\/2024.findings-emnlp.481"},{"key":"14","unstructured":"Volvovsky, S., Marcassa, M., and Panbiharwala, M. (2024). DFIN-SQL: Integrating Focused Schema with DIN-SQL for Superior Accuracy in Large-Scale Databases. ArXiv, abs\/2403.00872."},{"key":"15","unstructured":"Wang, B., Ren, C., Yang, J., Liang, X., Bai, J., Chai, L., Yan, Z., Zhang, Q., Yin, D., Sun, X., and Li, Z. (2025). MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL. In Proceedings of the 31st International Conference on Computational Linguistics, COLING 2025."},{"key":"16","unstructured":"Xu, L., Xie, H., Qin, S.-Z. J., Tao, X., and Wang, F. L. (2023). Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment. ArXiv, abs\/2312.12148."},{"key":"17","doi-asserted-by":"crossref","unstructured":"Yang, S., Su, Q., Li, Z., Li, Z., Mao, H., Liu, C., and Zhao, R. (2024). SQL-to-Schema Enhances Schema Linking in Text-to-SQL. In Database and Expert Systems Applications - 35th International Conference, DEXA 2024.","DOI":"10.1007\/978-3-031-68309-1_11"},{"key":"18","doi-asserted-by":"crossref","unstructured":"Yu, T., Zhang, R., Yang, K., Yasunaga, M., Wang, D., Li, Z., Ma, J., Li, I., Yao, Q., Roman, S., Zhang, Z., and Radev, D. (2018). Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMLP 2018.","DOI":"10.18653\/v1\/D18-1425"},{"key":"19","unstructured":"Zhang, T., Chen, C., Liao, C., Wang, J., Zhao, X., Yu, H., Wang, J., Li, J., and Shi, W. (2024). SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy. ArXiv, abs\/2407.14568."},{"key":"20","doi-asserted-by":"crossref","unstructured":"Zhong, R., Yu, T., and Klein, D. (2020). Semantic Evaluation for Text-to-SQL with Distilled Test Suites. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020.","DOI":"10.18653\/v1\/2020.emnlp-main.29"}],"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\/37234\/37017","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/sol.sbc.org.br\/index.php\/sbbd\/article\/download\/37234\/37017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T19:31:55Z","timestamp":1761075115000},"score":1,"resource":{"primary":{"URL":"https:\/\/sol.sbc.org.br\/index.php\/sbbd\/article\/view\/37234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":20,"URL":"https:\/\/doi.org\/10.5753\/sbbd.2025.247042","relation":{},"subject":[],"published":{"date-parts":[[2025,9,29]]}}}