{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T15:19:28Z","timestamp":1760800768093,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031758713"},{"type":"electronic","value":"9783031758720"}],"license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-75872-0_15","type":"book-chapter","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T05:02:23Z","timestamp":1729918943000},"page":"276-294","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Small, Medium, and\u00a0Large Language Models for\u00a0Text-to-SQL"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8970-0454","authenticated-orcid":false,"given":"Aiko","family":"Oliveira","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3391-7813","authenticated-orcid":false,"given":"Eduardo","family":"Nascimento","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0909-4432","authenticated-orcid":false,"given":"Jo\u00e3o","family":"Pinheiro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3899-0014","authenticated-orcid":false,"given":"Caio Viktor S.","family":"Avila","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2951-4972","authenticated-orcid":false,"given":"Gustavo","family":"Coelho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4763-8564","authenticated-orcid":false,"given":"Lucas","family":"Feij\u00f3","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0971-8572","authenticated-orcid":false,"given":"Yenier","family":"Izquierdo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9713-300X","authenticated-orcid":false,"given":"Grettel","family":"Garc\u00eda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6014-7256","authenticated-orcid":false,"given":"Luiz Andr\u00e9 P. Paes","family":"Leme","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1723-9897","authenticated-orcid":false,"given":"Melissa","family":"Lemos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0765-9636","authenticated-orcid":false,"given":"Marco A.","family":"Casanova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"15_CR1","unstructured":"Abdin, M.I., et\u00a0al.: Phi-3 technical report: a highly capable language model locally on your phone. Technical report MSR-TR-2024-12, Microsoft (2024). https:\/\/www.microsoft.com\/en-us\/research\/publication\/phi-3-technical-report-a-highly-capable-language-model-locally-on-your-phone\/"},{"key":"15_CR2","doi-asserted-by":"publisher","unstructured":"Affolter, K., Stockinger, K., Bernstein, A.: A comparative survey of recent natural language interfaces for databases. VLDB J. 28 (2019). https:\/\/doi.org\/10.1007\/s00778-019-00567-8","DOI":"10.1007\/s00778-019-00567-8"},{"key":"15_CR3","unstructured":"AI@Meta: Llama 3 model card. Technical report, Meta (2024). https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"15_CR4","unstructured":"Anthropic: Introducing the next generation of claude (2024). https:\/\/www.anthropic.com\/news\/claude-3-family"},{"key":"15_CR5","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-68309-1_8","volume-title":"DEXA 2024","author":"G Coelho","year":"2024","unstructured":"Coelho, G., et al.: Improving the accuracy of text-to-SQL tools based on large language models for real-world relational databases. In: Strauss, C., et al. (eds.) DEXA 2024. LNCS, vol. 14910, pp. 1\u201325. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-68309-1_8"},{"key":"15_CR6","unstructured":"DataBricks: Introducing DBRX: a new state-of-the-art open LLM (2024). https:\/\/platform.openai.com\/docs\/models\/overview"},{"key":"15_CR7","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI, et\u00a0al.: Deepseek LLM: scaling open-source language models with longtermism (2024). https:\/\/doi.org\/10.48550\/arXiv.2401.02954","DOI":"10.48550\/arXiv.2401.02954"},{"key":"15_CR8","doi-asserted-by":"publisher","unstructured":"Gan, Y., et al.: Towards robustness of text-to-SQL models against synonym substitution. CoRR abs\/2106.01065 (2021). https:\/\/doi.org\/10.48550\/arXiv.2106.01065","DOI":"10.48550\/arXiv.2106.01065"},{"key":"15_CR9","doi-asserted-by":"publisher","unstructured":"Gan, Y., Chen, X., Purver, M.: Exploring underexplored limitations of cross-domain text-to-SQL generalization. In: Proceedings of 2021 Conference on Empirical Methods in Natural Language Processing, pp. 8926\u20138931 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.702","DOI":"10.18653\/v1\/2021.emnlp-main.702"},{"key":"15_CR10","doi-asserted-by":"publisher","unstructured":"Gao, D., et al.: Text-to-SQL empowered by large language models: a benchmark evaluation. Proc. VLDB Endow. 17(5), 1132-1145 (2023). https:\/\/doi.org\/10.14778\/3641204.3641221","DOI":"10.14778\/3641204.3641221"},{"key":"15_CR11","unstructured":"GeminiTeam: Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (2024). https:\/\/storage.googleapis.com\/deepmind-media\/gemini\/gemini_v1_5_report.pdf"},{"key":"15_CR12","doi-asserted-by":"publisher","unstructured":"GemmaTeam: Gemma: Open models based on gemini research and technology. arXiv preprint (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.08295","DOI":"10.48550\/arXiv.2403.08295"},{"key":"15_CR13","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/978-981-99-8076-5_25","volume-title":"ICONIP 2023","author":"C Guo","year":"2024","unstructured":"Guo, C., et al.: Retrieval-augmented GPT-3.5-based text-to-SQL framework with sample-aware prompting and dynamic revision chain. In: Luo, B., Cheng, L., Wu, Z.G., Li, H., Li, C. (eds.) ICONIP 2023. LNCS, vol. 14452, pp. 341\u2013356. Springer, Singapore (2024). https:\/\/doi.org\/10.1007\/978-981-99-8076-5_25"},{"key":"15_CR14","doi-asserted-by":"publisher","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7b. arXiv preprint (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.06825","DOI":"10.48550\/arXiv.2310.06825"},{"key":"15_CR15","unstructured":"Lewis, P., et\u00a0al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 9459\u20139474. Curran Associates, Inc. (2020). https:\/\/api.semanticscholar.org\/CorpusID:218869575"},{"key":"15_CR16","unstructured":"Li, J., et al.: Can LLM already serve as a database interface? A big bench for large-scale database grounded text-to-SQLs. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. NIPS 2023. Curran Associates Inc., Red Hook (2024)"},{"key":"15_CR17","doi-asserted-by":"publisher","unstructured":"Manning, C.D.: Human language understanding & reasoning. Daedalus 151(2), 127\u2013138 (2022). https:\/\/doi.org\/10.1162\/daed_a_01905","DOI":"10.1162\/daed_a_01905"},{"key":"15_CR18","unstructured":"Nascimento, E.R.: Querying databases with natural language: the use of large language models for text-to-SQL tasks. Master\u2019s thesis, Dissertation presented to the Graduate Program in Informatics, PUC-Rio (2024)"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Nascimento, E.R., et al.: Text-to-SQL meets the real-world. In: Proceedings of the 26th International Conference on Enterprise Information Systems, vol. 1, pp. 61\u201372 (2024)","DOI":"10.5220\/0012555200003690"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Nascimento, E.R., et al.: My database user is a large language model. In: Proceedings of the 26th International Conference on Enterprise Information Systems, vol. 1, pp. 800\u2013806 (2024)","DOI":"10.5220\/0012697700003690"},{"key":"15_CR21","unstructured":"OpenAI: Openai models (2024). https:\/\/platform.openai.com\/docs\/models"},{"key":"15_CR22","unstructured":"Panda, S., Gozluklu, B.: Build a robust text-to-SQL solution generating complex queries, self-correcting, and querying diverse data sources. AWS Machine Learning Blog (2024)"},{"key":"15_CR23","doi-asserted-by":"publisher","unstructured":"Pourreza, M., Rafiei, D.: DTS-SQL: decomposed text-to-SQL with small large language models. arXiv preprint (2024). https:\/\/doi.org\/10.48550\/arXiv.2402.01117","DOI":"10.48550\/arXiv.2402.01117"},{"key":"15_CR24","unstructured":"Warkentin, T., Zhai, X., Peran, L.: Introducing paligemma, gemma 2, and an upgraded responsible AI toolkit. Technical report, Google (2024). https:\/\/developers.googleblog.com\/en\/gemma-family-and-toolkit-expansion-io-2024\/"},{"key":"15_CR25","doi-asserted-by":"publisher","unstructured":"Yu, T., et al.: Spider: a large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task. In: Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3911\u20133921 (2018). https:\/\/doi.org\/10.18653\/v1\/D18-1425","DOI":"10.18653\/v1\/D18-1425"},{"key":"15_CR26","doi-asserted-by":"publisher","unstructured":"Zhong, V., Xiong, C., Socher, R.: Seq2sql: generating structured queries from natural language using reinforcement learning. CoRR abs\/1709.00103 (2017). https:\/\/doi.org\/10.48550\/arXiv.1709.00103","DOI":"10.48550\/arXiv.1709.00103"}],"container-title":["Lecture Notes in Computer Science","Conceptual Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-75872-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T05:04:31Z","timestamp":1729919071000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-75872-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"ISBN":["9783031758713","9783031758720"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-75872-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"21 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ER","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Conceptual Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pittsburg, PA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"43","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"er2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/resources.sei.cmu.edu\/news-events\/events\/er2024\/cfp.cfm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}