{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T01:40:02Z","timestamp":1750988402434,"version":"3.41.0"},"reference-count":10,"publisher":"World Scientific Pub Co Pte Ltd","issue":"02","funder":[{"DOI":"10.13039\/501100004586","name":"FAPERJ","doi-asserted-by":"crossref","award":["E-26\/200.834\/2021"],"award-info":[{"award-number":["E-26\/200.834\/2021"]}],"id":[{"id":"10.13039\/501100004586","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002322","name":"CAPES","doi-asserted-by":"crossref","award":["88881.134081\/2016-01","88882.164913\/2010-01"],"award-info":[{"award-number":["88881.134081\/2016-01","88882.164913\/2010-01"]}],"id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003593","name":"CNPq","doi-asserted-by":"crossref","award":["305.587\/2021-8"],"award-info":[{"award-number":["305.587\/2021-8"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Semantic Computing"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:p> Large language models (LLMs) currently are the state of the art for pre-trained language models. LLMs have been applied to many tasks, including question and answering over Knowledge Graphs (KGs) and text-to-SPARQL, that is, the translation of Natural Language questions to SPARQL queries. With such motivation, this paper first describes preliminary experiments to evaluate the ability of ChatGPT to answer Natural Language questions over KGs. Based on these experiments, the paper introduces Auto-KGQA, an autonomous domain-independent framework based on LLMs for text-to-SPARQL. The framework selects fragments of the KG, which the LLM uses to translate the user\u2019s Natural Language question to a SPARQL query on the KG. The paper describes preliminary experiments with Auto-KGQA with ChatGPT that indicate that the framework substantially reduced the number of tokens passed to ChatGPT without sacrificing performance. Finally, the paper includes an evaluation of Auto-KGQA in a publicly available benchmark, which showed that the framework is competitive, achieving an improvement of 13.2% in accuracy with respect to the state of the art and a reduction of 51.12% in the number of tokens passed to the LLM. <\/jats:p>","DOI":"10.1142\/s1793351x25420048","type":"journal-article","created":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T15:09:42Z","timestamp":1741360182000},"page":"223-246","source":"Crossref","is-referenced-by-count":0,"title":["An Autonomous Domain-Independent Framework Based on LLMs for Text-to-SPARQL"],"prefix":"10.1142","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3899-0014","authenticated-orcid":false,"given":"Caio Viktor S.","family":"Avila","sequence":"first","affiliation":[{"name":"Departament of Computing, Federal University of Cear\u00e1, Fortaleza, Cear\u00e1 60440-900, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9370-8598","authenticated-orcid":false,"given":"V\u00e2nia M. P.","family":"Vidal","sequence":"additional","affiliation":[{"name":"Departament of Computing, Federal University of Cear\u00e1, Fortaleza, Cear\u00e1 60440-900, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9093-0428","authenticated-orcid":false,"given":"Wellington","family":"Franco","sequence":"additional","affiliation":[{"name":"Departament of Computing, Federal University of Cear\u00e1, Fortaleza, Cear\u00e1 60440-900, 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":"Department of Informatics, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22451-900, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"key":"S1793351X25420048BIB001","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324901002807"},{"key":"S1793351X25420048BIB002","doi-asserted-by":"publisher","DOI":"10.3390\/info12070271"},{"key":"S1793351X25420048BIB003","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-017-1100-y"},{"key":"S1793351X25420048BIB004","first-page":"1877","volume":"33","author":"Brown T.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S1793351X25420048BIB005","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47240-4_19"},{"key":"S1793351X25420048BIB007","volume-title":"Proc. Posters and Demo Track of the 19th Int. Conf. Semantic Systems (SEMANTiCS 2023), Leipzing, Germany, September 20 to 22, 2023, CEUR Workshop Proceedings","volume":"3526","author":"Kovriguina L.","year":"2023"},{"key":"S1793351X25420048BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC59802.2024.00050"},{"key":"S1793351X25420048BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"S1793351X25420048BIB014","doi-asserted-by":"publisher","DOI":"10.1002\/net.3230220105"},{"key":"S1793351X25420048BIB015","first-page":"9459","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Lewis P.","year":"2020"}],"container-title":["International Journal of Semantic Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S1793351X25420048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T00:59:59Z","timestamp":1750985999000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S1793351X25420048"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":10,"journal-issue":{"issue":"02","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10.1142\/S1793351X25420048"],"URL":"https:\/\/doi.org\/10.1142\/s1793351x25420048","relation":{},"ISSN":["1793-351X","1793-7108"],"issn-type":[{"type":"print","value":"1793-351X"},{"type":"electronic","value":"1793-7108"}],"subject":[],"published":{"date-parts":[[2025,4,24]]}}}