{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:38:36Z","timestamp":1761176316001,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>This paper describes the steps taken to construct a Natural Language interface based on Large Language Models (LLMs) for Busca360, an application in production at an energy company. The paper analyses how technologies developed for text-to-SQL perform on the Busca360 database and proposes solutions to overcome the limitations observed. The analysis is based on a benchmark that uses the Busca360 database and a set of 100 Natural Language (NL) questions and their ground truth SQL translations. The paper first investigates how text-to-SQL strategies perform on the Busca360 relational schema. The experiments showed that the performance of the strategies tested was significantly less than that reported in the leaderboards, mainly because schema linking failed. The Busca360 database was then equipped with views that rename the table and column names and have new columns that predefine joins that follow foreign keys. A second set of experiments using such views corroborated that schema linking largely improved, and the predefined joins reduced the complexity of the NL question translation. To enhance the results further, a third set of experiments tested a dynamic few-shot examples technique that prompted the LLM with examples of NL question\/SQL translation, retrieved from a synthetic dataset pre-computed from the database. The paper concludes by outlining the current LLM-based Natural Language interface using views and the dynamic few-shot examples technique, and leveraging the Busca360 database keyword search services.<\/jats:p>","DOI":"10.3233\/faia251458","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:03:26Z","timestamp":1761127406000},"source":"Crossref","is-referenced-by-count":0,"title":["The Quest for an LLM-Based Natural Language Interface for an Industrial Database"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1723-9897","authenticated-orcid":false,"given":"Melissa","family":"Lemos","sequence":"first","affiliation":[{"name":"Tecgraf Institute, PUC-Rio \u2013 Rio de Janeiro, RJ \u2013 Brazil"},{"name":"Department of Informatics, PUC-Rio \u2013 Rio de Janeiro, RJ \u2013 Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0971-8572","authenticated-orcid":false,"given":"Yenier T.","family":"Izquierdo","sequence":"additional","affiliation":[{"name":"Tecgraf Institute, PUC-Rio \u2013 Rio de Janeiro, RJ \u2013 Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9713-300X","authenticated-orcid":false,"given":"Grettel M.","family":"Garc\u00eda","sequence":"additional","affiliation":[{"name":"Tecgraf Institute, PUC-Rio \u2013 Rio de Janeiro, RJ \u2013 Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3391-7813","authenticated-orcid":false,"given":"Eduardo R.S.","family":"Nascimento","sequence":"additional","affiliation":[{"name":"Tecgraf Institute, PUC-Rio \u2013 Rio de Janeiro, RJ \u2013 Brazil"},{"name":"Department of Informatics, PUC-Rio \u2013 Rio de Janeiro, RJ \u2013 Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1932-296X","authenticated-orcid":false,"given":"Matheus O.","family":"Silva","sequence":"additional","affiliation":[{"name":"Department of Informatics, PUC-Rio \u2013 Rio de Janeiro, RJ \u2013 Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6355-7031","authenticated-orcid":false,"given":"Pedro H.T.","family":"Furtado","sequence":"additional","affiliation":[{"name":"Petrobras \u2013 Rio de Janeiro, RJ \u2013 Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0785-9606","authenticated-orcid":false,"given":"Michelle S.P.","family":"Facina","sequence":"additional","affiliation":[{"name":"Petrobras \u2013 Rio de Janeiro, RJ \u2013 Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0765-9636","authenticated-orcid":false,"given":"Marco A.","family":"Casanova","sequence":"additional","affiliation":[{"name":"Tecgraf Institute, PUC-Rio \u2013 Rio de Janeiro, RJ \u2013 Brazil"},{"name":"Department of Informatics, PUC-Rio \u2013 Rio de Janeiro, RJ \u2013 Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:03:26Z","timestamp":1761127406000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251458"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251458","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}