{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T13:00:01Z","timestamp":1780750801715,"version":"3.54.1"},"reference-count":64,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:00Z","timestamp":1780444800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:00Z","timestamp":1780444800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Semantic Web: \u2013 Interoperability, Usability, Applicability"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:p>The choice made for representing the inputs and outputs of generative pretrained language models (PLMs) can impact their fine-tuning on a new task. This article focuses on the fine-tuning and linearization process to generate facts extracted from text. On a restricted relation extraction (RE) task, we challenged five encoder\u2013decoder models, including BART, T5, CodeT5, FlanT5, and PileT5 by fine-tuning them on 13 linearization variations, including RDF standard syntaxes and variations thereof. Our benchmark covers the validity of the produced triples, the model\u2019s performance, the training behavior, and the resources needed. We show these PLMs can learn some syntaxes more easily than others, and we identify a promising \u201cTurtle Light\u201d syntax supporting the quick and robust learning of the RE task.<\/jats:p>","DOI":"10.1177\/22104968261452987","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T06:35:33Z","timestamp":1780554933000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Extensive Benchmark of Frugal Encoder\u2013Decoder Language Models for Datatype Properties Extraction and RDF Knowledge Graph Generation"],"prefix":"10.1177","volume":"17","author":[{"given":"C\u00e9lian","family":"Ringwald","sequence":"first","affiliation":[{"name":"Inria, Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, I3S"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0543-1232","authenticated-orcid":false,"given":"Fabien","family":"Gandon","sequence":"additional","affiliation":[{"name":"Inria, Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, I3S"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5959-5561","authenticated-orcid":false,"given":"Catherine","family":"Faron","sequence":"additional","affiliation":[{"name":"Inria, Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, I3S"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9064-0463","authenticated-orcid":false,"given":"Franck","family":"Michel","sequence":"additional","affiliation":[{"name":"Inria, Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, I3S"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9829-7401","authenticated-orcid":false,"given":"Hanna","family":"Abi Akl","sequence":"additional","affiliation":[{"name":"Inria, Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, I3S"},{"name":"Data ScienceTech Institute, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,6,3]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"crossref","unstructured":"Banerjee D. Nair P. Usbeck R. Biemann C. (2023). The role of output vocabulary in T2T LMs for SPARQL semantic parsing. In A. Rogers J. Boyd-Graber & N. Okazaki (Eds.) Findings of the Association for Computational Linguistics: ACL 2023 (pp. 12219\u201312228). Toronto Canada: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.774","DOI":"10.18653\/v1\/2023.findings-acl.774"},{"key":"e_1_3_3_3_1","doi-asserted-by":"crossref","unstructured":"Banerjee D. Nair P. A. Kaur J. N. Usbeck R. Biemann C. (2022). Modern baselines for SPARQL semantic parsing. In Proceedings of the 45th international ACM SIGIR conference on research and development in information retrieval SIGIR \u201922 (pp. 2260\u20132265). New York NY USA: Association for Computing Machinery. https:\/\/doi.org\/10.1145\/3477495.3531841","DOI":"10.1145\/3477495.3531841"},{"key":"e_1_3_3_4_1","unstructured":"Chung H. W. Hou L. Longpre S. Zoph B. Tay Y. Fedus W. Li Y. Wang X. Dehghani M. Brahma S. Webson A. Gu S. S. Dai Z. Suzgun M. Chen X. Chowdhery A. Castro-Ros A. Pellat M. Robinson K. \u2026 Wei J. (2022). Scaling instruction-finetuned language models. https:\/\/arxiv.org\/abs\/2210.11416."},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45563-x"},{"key":"e_1_3_3_6_1","doi-asserted-by":"crossref","unstructured":"Devlin J. Chang M. W. Lee K. Toutanova K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In J. Burstein C. Doran & T. Solorio (Eds.) Proceedings of the 2019 conference of the North American chapter of the Association for Computational Linguistics: Human language technologies (Vol. 1) (Long and Short Papers) (pp. 4171\u20134186). Minneapolis MN: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_3_8_1","unstructured":"Efeoglu S. Paschke A. (2024). Retrieval-augmented generation-based relation extraction. ArXiv abs\/2404.13397. https:\/\/api.semanticscholar.org\/CorpusID:269292881"},{"key":"e_1_3_3_9_1","doi-asserted-by":"crossref","unstructured":"Elsahar H. Vougiouklis P. Remaci A. Gravier C. Hare J. Simperl E. Laforest F. (2018). T-REx: A large scale alignment of natural language with knowledge base triples. In LREC2018. Miyazaki Japan: European Language Resources Association (ELRA). https:\/\/aclanthology.org\/L18-1544","DOI":"10.63317\/2yu5nu76n7bu"},{"key":"e_1_3_3_10_1","unstructured":"Frey J. Meyer L. P. Arndt N. Brei F. Bulert K. (2023). Benchmarking the abilities of large language models for RDF knowledge graph creation and comprehension: How well do LLMs speak turtle? ArXiv abs\/2309.17122. https:\/\/api.semanticscholar.org\/CorpusID:263310661"},{"key":"e_1_3_3_11_1","unstructured":"Gallardo A. P. Consoli S. Ceresa M. Hulsman R. Bertolini L. (2024). On constructing biomedical text-to-graph systems with large language models. In S. Tiwari N. Mihindukulasooriya F. Osborne D. Kontokostas J. D\u2019Souza M. Kejriwal M.A. Pellegrino A. Rula J. E. L. Gayo M. Cochez & M. Alam (Eds.) Joint proceedings of the 3rd international workshop on knowledge graph generation from text (TEXT2KG) and Data Quality meets Machine Learning and knowledge graphs (DQMLKG) co-located with the Extended Semantic Web Conference (ESWC 2024) Hersonissos Greece May 26\u201330 2024 CEUR Workshop Proceedings (Vol. 3747 p. 12). CEUR-WS.org. https:\/\/ceur-ws.org\/Vol-3747\/text2kg_paper10.pdf"},{"key":"e_1_3_3_12_1","doi-asserted-by":"crossref","unstructured":"Gardent C. Shimorina A. Narayan S. Perez-Beltrachini L. (2017). Creating training corpora for NLG micro-planners. In Proceedings of the 55th annual meeting of the Association for Computational Linguistics (Vol. 1 Long Papers) (pp. 179\u2013188). Vancouver Canada: ACL. https:\/\/doi.org\/10.18653\/v1\/p17-1017","DOI":"10.18653\/v1\/P17-1017"},{"key":"e_1_3_3_13_1","doi-asserted-by":"crossref","unstructured":"Geng S. Josifoski M. Peyrard M. West R. (2023). Grammar-constrained decoding for structured NLP tasks without finetuning. In H. Bouamor J. Pino & K. Bali (Eds.) Proceedings of the 2023 conference on empirical methods in natural language processing. Singapore: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.674","DOI":"10.18653\/v1\/2023.emnlp-main.674"},{"key":"e_1_3_3_14_1","unstructured":"Grangier D. Katharopoulos A. Ablin P. Hannun A. (2024). Need a small specialized language model? Plan early! https:\/\/arxiv.org\/abs\/2402.01093"},{"key":"e_1_3_3_15_1","doi-asserted-by":"crossref","unstructured":"Harbecke D. Chen Y. Hennig L. Alt C. (2022). Why only micro-F1? Class weighting of measures for relation classification. In T. Shavrina V. Mikhailov V. Malykh E. Artemova O. Serikov & V. Protasov (Eds.) Proceedings of NLP power! The first workshop on efficient benchmarking in NLP (pp. 32\u201341). Dublin Ireland: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2022.nlppower-1.4","DOI":"10.18653\/v1\/2022.nlppower-1.4"},{"key":"e_1_3_3_16_1","unstructured":"Hofer M. Frey J. Rahm E. (2024). Towards self-configuring knowledge graph construction pipelines using LLMs\u2014A case study with RML. In D. Chaves-Fraga A. Dimou A. Iglesias-Molina U. Serles & D. V. Assche (Eds.) Proceedings of the 5th international workshop on knowledge graph construction co-located with 21st Extended Semantic Web Conference (ESWC 2024) Hersonissos Greece May 27 2024 CEUR Workshop Proceedings (Vol. 3718). CEUR-WS.org. https:\/\/ceur-ws.org\/Vol-3718\/paper6.pdf"},{"key":"e_1_3_3_17_1","doi-asserted-by":"crossref","unstructured":"Hofer M. Obraczka D. Saeedi A. K\u00f6pcke H. Rahm E. (2023). Construction of knowledge graphs: State and challenges. ArXiv:2302.11509 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2302.11509; http:\/\/arxiv.org\/abs\/2302.11509","DOI":"10.2139\/ssrn.4605059"},{"key":"e_1_3_3_18_1","doi-asserted-by":"crossref","unstructured":"Huguet Cabot P. L. Navigli R. (2021). REBEL: Relation extraction by end-to-end language generation. In M. F. Moens X. Huang L. Specia & S. W. T. Yih (Eds.) Findings of the Association for Computational Linguistics: EMNLP 2021 (pp. 2370\u20132381). Punta Cana Dominican Republic: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.204","DOI":"10.18653\/v1\/2021.findings-emnlp.204"},{"key":"e_1_3_3_19_1","unstructured":"Hussam Ghanem C. C. (2024). Fine-tuning vs. prompting: Evaluating the knowledge graph construction with LLMs. https:\/\/ceur-ws.org\/Vol-3747\/text2kg_paper7.pdf"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_3_21_1","unstructured":"Jin B. Liu G. Han C. Jiang M. Ji H. Han J. (2023). Large language models on graphs: A comprehensive survey. ArXiv:2312.02783 [cs]. http:\/\/arxiv.org\/abs\/2312.02783"},{"key":"e_1_3_3_22_1","doi-asserted-by":"crossref","unstructured":"Josifoski M. De Cao N. Peyrard M. Petroni F. West R. (2022). GenIE: Generative information extraction. In M. Carpuat M. C. de Marneffe & I. V. Meza Ruiz (Eds.) Proceedings of the 2022 conference of the North American chapter of the Association for Computational Linguistics: Human language technologies (pp. 4626\u20134643). Seattle USA: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.342","DOI":"10.18653\/v1\/2022.naacl-main.342"},{"key":"e_1_3_3_23_1","doi-asserted-by":"crossref","unstructured":"Josifoski M. Sakota M. Peyrard M. West R. (2023). Exploiting asymmetry for synthetic training data generation: SynthIE and the case of information extraction. In H. Bouamor J. Pino & K. Bali (Eds.) Proceedings of the 2023 conference on empirical methods in natural language processing (pp. 1555\u20131574). Singapore: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.96","DOI":"10.18653\/v1\/2023.emnlp-main.96"},{"key":"e_1_3_3_24_1","unstructured":"Kandpal N. Deng H. Roberts A. Wallace E. Raffel C. (2023). Large language models struggle to learn long-tail knowledge. In Proceedings of the 40th international conference on machine learning ICML\u201923. JMLR.org."},{"key":"e_1_3_3_25_1","doi-asserted-by":"crossref","unstructured":"Ke P. Ji H. Ran Y. Cui X. Wang L. Song L. Zhu X. Huang M. (2021). JointGT: Graph-text joint representation learning for text generation from knowledge graphs. In C. Zong F. Xia W. Li & R. Navigli (Eds.) Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (pp. 2526\u20132538). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.223","DOI":"10.18653\/v1\/2021.findings-acl.223"},{"key":"e_1_3_3_26_1","doi-asserted-by":"crossref","unstructured":"Lehmann J. Meloni A. Motta E. Osborne F. Recupero D. R. Salatino A. A. Vahdati S. (2024). Large language models for scientific question answering: An extensive analysis of the SCIQA benchmark. In A. Mero\u00f1o Pe\u00f1uela A. Dimou R. Troncy O. Hartig M. Acosta M. Alam H. Paulheim & P. Lisena (Eds.) The semantic web (pp. 199\u2013217). Cham: Springer Nature Switzerland.","DOI":"10.1007\/978-3-031-60626-7_11"},{"key":"e_1_3_3_27_1","unstructured":"Lewis M. Liu Y. Goyal N. Ghazvininejad M. Mohamed A. Levy O. Stoyanov V. Zettlemoyer L. (2019). BART: Denoising sequence-to-sequence pre-training for natural language generation translation and comprehension. ArXiv:1910.13461 [cs stat]. https:\/\/doi.org\/10.48550\/arXiv.1910.13461; http:\/\/arxiv.org\/abs\/1910.13461"},{"key":"e_1_3_3_28_1","doi-asserted-by":"crossref","unstructured":"Li G. Wang P. Ke W. Guo Y. Ji K. Shang Z. Liu J. Xu Z. (2024). Recall retrieve and reason: Towards better in-context relation extraction. In K. Larson (Ed.) Proceedings of the thirty-third international joint conference on artificial intelligence IJCAI-24 (pp. 6368\u20136376). International Joint Conferences on Artificial Intelligence Organization. https:\/\/doi.org\/10.24963\/ijcai.2024\/704","DOI":"10.24963\/ijcai.2024\/704"},{"key":"e_1_3_3_29_1","unstructured":"Li X. Polat F. Groth P. (2025). Do instruction-tuned large language models help with relation extraction? In S. Razniewski J. C. Kalo S. Singhania & J. Z. Pan (Eds.) Joint proceedings of the 1st workshop on knowledge base construction from pre-trained language models (KBC-LM) and the 2nd challenge on language models for knowledge base construction (LM-KBC) CEUR Workshop Proceedings (Vol. 3577). CEUR. https:\/\/ceur-ws.org\/Vol-3577\/##paper4"},{"key":"e_1_3_3_30_1","doi-asserted-by":"crossref","unstructured":"Liu M. X. Liu F. Fiannaca A. J. Koo T. Dixon L. Terry M. Cai C. J. (2024a). \u201cWe need structured output\u201d: Towards user-centered constraints on large language model output. In Extended abstracts of the chi conference on human factors in computing systems CHI EA \u201924. New York NY USA: Association for Computing Machinery. https:\/\/doi.org\/10.1145\/3613905.3650756","DOI":"10.1145\/3613905.3650756"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103809"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.395"},{"key":"e_1_3_3_34_1","unstructured":"Lu Z. Li X. Cai D. Yi R. Liu F. Zhang X. Lane N. D. Xu M. (2024). Small language models: Survey measurements and insights. https:\/\/arxiv.org\/abs\/2409.15790"},{"key":"e_1_3_3_35_1","article-title":"Assessing SPARQL capabilities of Large Language Models","author":"Meyer L.-P.","year":"2025","unstructured":"Meyer L.-P., Frey J., Brei F., Arndt N. (2025). Assessing SPARQL capabilities of Large Language Models. arXiv 2409.05925. https:\/\/arxiv.org\/abs\/2409.05925","journal-title":"arXiv 2409.05925"},{"key":"e_1_3_3_36_1","doi-asserted-by":"crossref","unstructured":"Meyer L. P. Stadler C. Frey J. Radtke N. Junghanns K. Meissner R. Dziwis G. Bulert K. Martin M. (2024). LLM-assisted knowledge graph engineering: Experiments with ChatGPT. In C. Zinke-Wehlmann & J. Friedrich (Eds.) First working conference on artificial intelligence development for a resilient and sustainable tomorrow (pp. 103\u2013115). Wiesbaden: Springer Fachmedien Wiesbaden. https:\/\/doi.org\/10.1007\/978-3-658-43705-3_8","DOI":"10.1007\/978-3-658-43705-3_8"},{"key":"e_1_3_3_37_1","doi-asserted-by":"crossref","unstructured":"Mihindukulasooriya N. Sava M. Rossiello G. Chowdhury M. F. M. Yachbes I. Gidh A. Duckwitz J. Nisar K. Santos M. Gliozzo A. (2022). Knowledge graph induction enabling recommending and trend analysis: A corporate research community use case. In The Semantic Web\u2014ISWC 2022: 21st international semantic web conference Virtual Event October 23\u201327 2022 Proceedings (pp. 827\u2013844). Berlin Heidelberg: Springer-Verlag. https:\/\/doi.org\/10.1007\/978-3-031-19433-7_47","DOI":"10.1007\/978-3-031-19433-7_47"},{"key":"e_1_3_3_38_1","doi-asserted-by":"crossref","unstructured":"Mihindukulasooriya N. Tiwari S. Enguix C. F. Lata K. (2023). Text2kgbench: A benchmark for ontology-driven knowledge graph generation from text. https:\/\/arxiv.org\/abs\/2308.02357","DOI":"10.1007\/978-3-031-47243-5_14"},{"key":"e_1_3_3_39_1","unstructured":"Minaee S. Mikolov T. Nikzad N. Chenaghlu M. Socher R. Amatriain X. Gao J. (2024). Large language models: A survey."},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-94575-5_25"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-021-09917-7"},{"key":"e_1_3_3_42_1","unstructured":"Paolini G. Athiwaratkun B. Krone J. Ma J. Achille A. dos Santos R. Anubhai C. N. Xiang B. Soatto S. (2021). Structured prediction as translation between augmented natural languages. In 9th International conference on learning representations ICLR 2021."},{"key":"e_1_3_3_43_1","doi-asserted-by":"crossref","unstructured":"Papineni K. Roukos S. Ward T. Zhu W. J. (2002). BLEU: A method for automatic evaluation of machine translation. In P. Isabelle E. Charniak & D. Lin (Eds.) Proceedings of the 40th annual meeting of the Association for Computational Linguistics (pp. 311\u2013318). Philadelphia PA USA: Association for Computational Linguistics. https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_3_44_1","doi-asserted-by":"crossref","unstructured":"Patel A. Raffel C. Callison-Burch C. (2024). DataDreamer: A tool for synthetic data generation and reproducible LLM workflows. In L. W. Ku A. Martins & V. Srikumar (Eds.) Proceedings of the 62nd annual meeting of the Association for Computational Linguistics (Vol. 1 Long Papers) (pp. 3781\u20133799). Bangkok Thailand: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.208","DOI":"10.18653\/v1\/2024.acl-long.208"},{"key":"e_1_3_3_45_1","unstructured":"Raffel C. Shazeer N. Roberts A. Lee K. Narang S. Matena M. Zhou Y. Li W. Liu P. J. (2023). Exploring the limits of transfer learning with a unified text-to-text transformer. ArXiv:1910.10683 [cs stat]. http:\/\/arxiv.org\/abs\/1910.10683"},{"key":"e_1_3_3_46_1","article-title":"A systematic literature review on RDF triple generation from natural language text","author":"Regino A. G.","year":"2025","unstructured":"Regino A. G., Rossanez A., da Silva Torres R., dos Reis J. C. (2025). A systematic literature review on RDF triple generation from natural language text. Semantic Web Journal.","journal-title":"Semantic Web Journal"},{"key":"e_1_3_3_47_1","doi-asserted-by":"crossref","unstructured":"Reyd S. Zouaq A. (2023). Assessing the generalization capabilities of neural machine translation models for SPARQL query generation. In T. R. Payne V. Presutti G. Qi M. Poveda-Villal\u00f3n G. Stoilos L. Hollink Z. Kaoudi G. Cheng & J. Li (Eds.) The Semantic Web\u2014ISWC 2023\u201422nd international semantic web conference Athens Greece November 6\u201310 2023 Proceedings Part I Lecture Notes in Computer Science (Vol. 14265 pp. 484\u2013501). Springer. https:\/\/doi.org\/10.1007\/978-3-031-47240-4_26","DOI":"10.1007\/978-3-031-47240-4_26"},{"key":"e_1_3_3_48_1","unstructured":"Ringwald C. Gandon F. Faron C. Michel F. Akl H. A. (2025a). 12 shades of RDF: Impact of syntaxes on data extraction with language models. In A. Mero\u00f1o Pe\u00f1uela O. Corcho P. Groth E. Simperl V. Tamma A. G. Nuzzolese M. Poveda-Villal\u00f3n M. Sabou V. Presutti I. Celino A. Revenko J. Raad B. Sartini & P. Lisena (Eds.) The Semantic Web: ESWC 2024 satellite events (pp. 81\u201391). Cham: Springer Nature Switzerland."},{"key":"e_1_3_3_49_1","doi-asserted-by":"crossref","unstructured":"Ringwald C. Gandon F. Faron C. Michel F. Akl H. A. (2025b). Overcoming the generalization limits of SLM finetuning for shape-based extraction of datatype and object properties. In KCAP 2025\u2014The thirteenth international conference on knowledge capture-10\u2014Association for Computing Machinery. Dayton: OH USA: ACM. https:\/\/hal.science\/hal-05285428. Accepted at KCAP2025\u2014Preprint version not updated with reviews.","DOI":"10.1145\/3731443.3771342"},{"key":"e_1_3_3_50_1","doi-asserted-by":"crossref","unstructured":"\u0160akota M. West R. (2025). Combining constrained and unconstrained decoding via boosting: BoostCD and its application to information extraction. https:\/\/arxiv.org\/abs\/2506.14901","DOI":"10.18653\/v1\/2025.emnlp-main.926"},{"key":"e_1_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.websem.2021.100679"},{"key":"e_1_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241741"},{"key":"e_1_3_3_53_1","unstructured":"Sun K. Qi P. Zhang Y. Liu L. Wang W. Y. Huang Z. (2023). Tokenization consistency matters for generative models on extractive NLP tasks. ArXiv:2212.09912 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2212.09912; http:\/\/arxiv.org\/abs\/2212.09912"},{"key":"e_1_3_3_54_1","unstructured":"Sutawika L. Komatsuzaki A. Raffel C. (2024). Pile-T5. Blog post. https:\/\/blog.eleuther.ai\/pile-t5\/"},{"key":"e_1_3_3_55_1","doi-asserted-by":"crossref","unstructured":"Taill\u00e9 B. Guigue V. Scoutheeten G. Gallinari P. (2020). Let\u2019s stop incorrect comparisons in end-to-end relation extraction! In B. Webber T. Cohn Y. He & Y. Liu (Eds.) Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP) (pp. 3689\u20133701). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.301","DOI":"10.18653\/v1\/2020.emnlp-main.301"},{"key":"e_1_3_3_56_1","doi-asserted-by":"crossref","unstructured":"Wadhwa S. Amir S. Wallace B. (2023). Revisiting relation extraction in the era of large language models. In A. Rogers J. Boyd-Graber & N. Okazaki (Eds.) Proceedings of the 61st annual meeting of the Association for Computational Linguistics (Vol. 1 Long Papers) (pp. 15566\u201315589). Toronto Canada: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.868","DOI":"10.18653\/v1\/2023.acl-long.868"},{"key":"e_1_3_3_57_1","doi-asserted-by":"crossref","unstructured":"Wang C. Liu X. Chen Z. Hong H. Tang J. Song D. (2022). DeepStruct: Pretraining of language models for structure prediction. In S. Muresan P. Nakov & A. Villavicencio (Eds.) Findings of the Association for Computational Linguistics: ACL 2022 (pp. 803\u2013823). Dublin Ireland: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.67","DOI":"10.18653\/v1\/2022.findings-acl.67"},{"key":"e_1_3_3_58_1","unstructured":"Wang F. Zhang Z. Zhang X. Wu Z. Mo T. Lu Q. Wang W. Li R. Xu J. Tang X. He Q. Ma Y. Huang M. Wang S. (2024). A comprehensive survey of small language models in the era of large language models: Techniques enhancements applications collaboration with LLMs and trustworthiness. https:\/\/arxiv.org\/abs\/2411.03350"},{"key":"e_1_3_3_59_1","doi-asserted-by":"crossref","unstructured":"Wang Y. Wang W. Joty S. Hoi S. C. H. (2021). CodeT5: Identifier-aware unified pre-trained encoder\u2013decoder models for code understanding and generation. https:\/\/arxiv.org\/abs\/2109.00859","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_3_60_1","doi-asserted-by":"crossref","unstructured":"Wu C. Chen L. (2020). Utber: Utilizing fine-grained entity types to relation extraction with distant supervision. In 2020 IEEE International conference on smart data services (SMDS) (pp. 63\u201371). https:\/\/doi.org\/10.1109\/SMDS49396.2020.00015","DOI":"10.1109\/SMDS49396.2020.00015"},{"key":"e_1_3_3_61_1","doi-asserted-by":"crossref","unstructured":"Yao Y. Ye D. Li P. Han X. Lin Y. Liu Z. Liu Z. Huang L. Zhou J. Sun M. (2019). DocRED: A large-scale document-level relation extraction dataset. In Proceedings of the 57th annual meeting of the ACL (pp. 764\u2013777). Florence Italy: ACL. https:\/\/doi.org\/10.18653\/v1\/p19-1074","DOI":"10.18653\/v1\/P19-1074"},{"key":"e_1_3_3_62_1","unstructured":"Ye H. Zhang N. Chen H. Chen H. (2022). Generative knowledge graph construction: A review. CoRR abs\/2210.12714. https:\/\/doi.org\/10.48550\/arXiv.2210.12714"},{"issue":"1","key":"e_1_3_3_63_1","first-page":"77","article-title":"Linked data quality of DBpedia, Freebase, OpenCyc, Wikidata, and YAGO","volume":"9","author":"Zaveri A.","year":"2018","unstructured":"Zaveri A., Kontokostas D., Hellmann S., Umbrich J., F\u00e4rber M., Bartscherer F., Menne C., Rettinger A., Zaveri A., Kontokostas D., Hellmann S., Umbrich J. (2018). Linked data quality of DBpedia, Freebase, OpenCyc, Wikidata, and YAGO. Semantic web, 9(1), 77\u2013129. https:\/\/doi.org\/10.3233\/SW-170275","journal-title":"Semantic web"},{"key":"e_1_3_3_64_1","doi-asserted-by":"crossref","unstructured":"Zaveri A. Kontokostas D. Sherif M. A. B\u00fchmann L. Morsey M. Auer S. Lehmann J. (2013). User-driven quality evaluation of DBpedia. In Proceedings of the 9th international conference on semantic systems I-SEMANTICS \u201913 (pp. 97\u2013104). New York NY USA: Association for Computing Machinery. https:\/\/doi.org\/10.1145\/2506182.2506195","DOI":"10.1145\/2506182.2506195"},{"key":"e_1_3_3_65_1","unstructured":"Zhang B. Reklos I. Jain N. Pe\u00f1uela A. M. Simperl E. (2023). Using large language models for knowledge engineering (LLMKE): A case study on Wikidata. https:\/\/arxiv.org\/abs\/2309.08491"}],"container-title":["Semantic Web: \u2013 Interoperability, Usability, Applicability"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/22104968261452987","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/22104968261452987","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/22104968261452987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T12:19:38Z","timestamp":1780748378000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/22104968261452987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,3]]},"references-count":64,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1177\/22104968261452987"],"URL":"https:\/\/doi.org\/10.1177\/22104968261452987","relation":{},"ISSN":["1570-0844","2210-4968"],"issn-type":[{"value":"1570-0844","type":"print"},{"value":"2210-4968","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,3]]},"article-number":"22104968261452987"}}