{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T19:27:48Z","timestamp":1787599668014,"version":"build-2736575974"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Research Foundation of Korea(NRF) grant"},{"name":"Korea Government","award":["RS-2023-00222663"],"award-info":[{"award-number":["RS-2023-00222663"]}]},{"name":"BK21 Fostering Outstanding Universities for Research"},{"name":"Ministry of Education"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3722873","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T19:15:32Z","timestamp":1786562132000},"page":"126645-126660","source":"Crossref","is-referenced-by-count":0,"title":["NL2SQL+: An Extended Framework for SQL Generation With On-Demand Embedded ML Functions"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4449-2381","authenticated-orcid":false,"given":"Jisoo","family":"Jang","sequence":"first","affiliation":[{"name":"Seoul National University","place":["Seoul, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2849-4903","authenticated-orcid":false,"given":"Mingyoo","family":"Son","sequence":"additional","affiliation":[{"name":"Seoul National University","place":["Seoul, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0496-3479","authenticated-orcid":false,"given":"Wen-Syan","family":"Li","sequence":"additional","affiliation":[{"name":"Seoul National University","place":["Seoul, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Introduction to AI and ML in BigQuery | Google Cloud","author":"BigQuery","year":"2025"},{"key":"ref2","volume-title":"Amazon Redshift ML","author":"Services","year":"2025"},{"key":"ref3","volume-title":"Azure Synapse Analytics | Microsoft Azure","author":"Azure","year":"2025"},{"key":"ref4","volume-title":"Postgres + GPUs for ML\/AI Applications","author":"Team","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1425"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1835"},{"key":"ref8","volume-title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","author":"Lei","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2026.3657851"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00247"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3592032"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlp4convai-1.5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.257"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2168"},{"key":"ref15","first-page":"1","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lundberg"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IISA.2015.7388053"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref18","first-page":"1","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref19","first-page":"1","article-title":"Seq2SQL: Generating structured queries from natural language using reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhong"},{"key":"ref20","first-page":"1","article-title":"ReAct: Synergizing reasoning and acting in language models","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Yao"},{"key":"ref21","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lewis"},{"key":"ref22","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref23","volume-title":"Hello GPT-4O","year":"2024"},{"key":"ref24","volume-title":"GPT-4O Mini: Advancing Cost-Efficient Intelligence","year":"2024"},{"key":"ref25","volume-title":"Gemini: A Family of Highly Capable Multimodal Models","author":"Team","year":"2023"},{"key":"ref26","article-title":"The Llama 3 herd of models","volume-title":"arXiv:2407.21783","author":"Grattafiori","year":"2024"},{"key":"ref27","volume-title":"OpenAI O1-Mini","year":"2024"},{"key":"ref28","volume-title":"OpenAI O3-Mini","year":"2025"},{"key":"ref29","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref30","first-page":"1","article-title":"Let\u2019s verify step by step","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Lightman"},{"key":"ref31","volume-title":"Introducing GPT-5","year":"2026"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075823"},{"key":"ref33","first-page":"1050","article-title":"Learning to parse database queries using inductive logic programming","volume-title":"Proc. Nat. Conf. Artif. Intell.","author":"Zelle"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367510"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.14778\/3007263.3007279"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3399579.3399866"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611559"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.14778\/3749646.3749685"},{"key":"ref39","first-page":"1","article-title":"Palimpzest: Optimizing AI-powered analytics with declarative query processing","volume-title":"Proc. Conf. Innov. Data Syst. Res. (CIDR)","author":"Liu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3654732"},{"key":"ref41","first-page":"1","article-title":"Efficient and robust automated machine learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Feurer"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3589292"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.14778\/3583140.3583165"},{"key":"ref44","volume-title":"SQLGlot API Documentation","author":"Mao","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11652980.pdf?arnumber=11652980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T19:14:26Z","timestamp":1787598866000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11652980\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3722873","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}