{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T21:12:31Z","timestamp":1769807551842,"version":"3.49.0"},"reference-count":30,"publisher":"World Scientific Pub Co Pte Ltd","issue":"04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2026,3,30]]},"abstract":"<jats:p>Large Language Models (LLMs) have achieved remarkable success in natural language understanding and generation. However, generating structured information from unstructured text remains challenging due to format instability, low extraction accuracy, poor generalization, and the high cost of model fine-tuning. In practical applications, these issues cause difficulties in accurately extracting structured information, especially limiting performance in cross-domain and complex scenarios. To address these issues, we propose PT4Struct (Prompt Tuning for Structured Information), a unified framework that leverages prompt tuning to guide LLMs in automatically generating structured outputs such as tables, JSON objects, and key-value pairs. Instead of modifying model parameters, PT4Struct designs task-specific prompts to steer the model toward format-compliant outputs, significantly reducing training and deployment costs. The framework exhibits strong generalizability and extensibility across various structured information generation tasks. Experimental results demonstrate that PT4Struct outperforms existing methods in accuracy, controllability, and cross-task adaptability, offering an efficient, flexible, and cost-effective solution for structured data generation. This method provides an efficient and generalizable solution for multi-domain structured information extraction, with potential for extension to more complex text types in future work.<\/jats:p>","DOI":"10.1142\/s0218001425590232","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T04:21:32Z","timestamp":1762230092000},"source":"Crossref","is-referenced-by-count":0,"title":["A Prompt-Tuned Large Language Model Framework for Automated Generation of Structured Information"],"prefix":"10.1142","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1563-3292","authenticated-orcid":false,"given":"Chenyu","family":"Sun","sequence":"first","affiliation":[{"name":"Hebei Institute of Communications Shijiazhuang, Hebei 050000, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"Hebei Institute of Communications Shijiazhuang, Hebei 050000, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"S0218001425590232BIB001","doi-asserted-by":"publisher","DOI":"10.1109\/ICCECE58645.2024.10497313"},{"key":"S0218001425590232BIB002","first-page":"1877","volume":"33","author":"Brown T.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0218001425590232BIB003","unstructured":"A. Ecoffet, J. Huizinga, J. Lehman, K. O. Stanley and J. Clune, Go-explore: A new approach for hard-exploration problems, preprint (2019), arXiv:1901.10995."},{"key":"S0218001425590232BIB004","first-page":"179","volume-title":"55th Annual Meeting of the Association for Computational Linguistics, ACL 2017","author":"Gardent C.","year":"2017"},{"key":"S0218001425590232BIB005","doi-asserted-by":"crossref","unstructured":"C. Hokamp and Q. Liu, Lexically constrained decoding for sequence generation using grid beam search, preprint (2017), arXiv:1704.07138.","DOI":"10.18653\/v1\/P17-1141"},{"key":"S0218001425590232BIB006","unstructured":"Z. Huang, W. Xu and K. Yu, Bidirectional lstm-crf models for sequence tagging, preprint (2015), arXiv:1508.01991."},{"key":"S0218001425590232BIB007","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"S0218001425590232BIB008","doi-asserted-by":"crossref","unstructured":"K. Kolluru\n                      et al\n                      ., Openie6: Iterative grid labeling and coordination analysis for open information extraction, preprint (2020), arXiv:2010.03147.","DOI":"10.18653\/v1\/2020.emnlp-main.306"},{"issue":"2","key":"S0218001425590232BIB009","first-page":"282","volume-title":"Int. Conf. Machine Learning","volume":"1","author":"Lafferty J.","year":"2001"},{"key":"S0218001425590232BIB010","doi-asserted-by":"crossref","unstructured":"G. Lample, M. Ballesteros, S. Subramanian, K. Kawakami and C. Dyer, Neural architectures for named entity recognition, preprint (2016), arXiv:1603.01360.","DOI":"10.18653\/v1\/N16-1030"},{"key":"S0218001425590232BIB011","unstructured":"M. Lee, J. Min, W. Lee and Y. Lee, Structured language generation model for robust structure prediction, preprint (2024), arXiv:2402.08971."},{"key":"S0218001425590232BIB012","doi-asserted-by":"crossref","unstructured":"B. Lester, R. Al-Rfou and N. Constant, The power of scale for parameter-efficient prompt tuning, preprint (2021), arXiv:2104.08691.","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"S0218001425590232BIB013","doi-asserted-by":"crossref","unstructured":"C. Liang, J. Berant, Q. Le, K. D. Forbus and N. Lao, Neural symbolic machines: Learning semantic parsers on freebase with weak supervision, preprint (2016), arXiv:1611.00020.","DOI":"10.18653\/v1\/P17-1003"},{"key":"S0218001425590232BIB014","doi-asserted-by":"crossref","unstructured":"X. Liu, K. Ji, Y. Fu, W. L. Tam, Z. Du, Z. Yang and J. Tang, P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks, preprint (2021), arXiv:2110.07602.","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"S0218001425590232BIB015","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"S0218001425590232BIB016","doi-asserted-by":"crossref","unstructured":"Y. Lu, Q. Liu, D. Dai, X. Xiao, H. Lin, X. Han, L. Sun and H. Wu, Unified structure generation for universal information extraction, preprint (2022), arXiv:2203.12277.","DOI":"10.18653\/v1\/2022.acl-long.395"},{"key":"S0218001425590232BIB017","doi-asserted-by":"crossref","unstructured":"Y. Luan, L. He, M. Ostendorf and H. Hajishirzi, Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction, preprint (2018), arXiv:1808.09602.","DOI":"10.18653\/v1\/D18-1360"},{"key":"S0218001425590232BIB018","doi-asserted-by":"crossref","unstructured":"J. Novikova, O. Du\u0161ek, A. C. Curry and V. Rieser, Why we need new evaluation metrics for nlg, preprint (2017), arXiv:1707.06875.","DOI":"10.18653\/v1\/D17-1238"},{"key":"S0218001425590232BIB019","doi-asserted-by":"crossref","unstructured":"P. Pasupat and P. Liang, Compositional semantic parsing on semi-structured tables, preprint (2015), arXiv:1508.00305.","DOI":"10.3115\/v1\/P15-1142"},{"key":"S0218001425590232BIB020","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3571210"},{"key":"S0218001425590232BIB021","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3563928"},{"issue":"140","key":"S0218001425590232BIB022","first-page":"1","volume":"21","author":"Raffel C.","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"S0218001425590232BIB023","unstructured":"E. F. Sang and F. De Meulder, Introduction to the conll-2003 shared task: Language-independent named entity recognition, preprint (2003), arXiv:cs\/0306050."},{"key":"S0218001425590232BIB024","doi-asserted-by":"crossref","unstructured":"T. Schick and H. Sch\u00fctze, Exploiting cloze questions for few shot text classification and natural language inference, preprint (2020), arXiv:2001.07676.","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"S0218001425590232BIB025","doi-asserted-by":"crossref","unstructured":"T. Shin, Y. Razeghi, R. L. Logan IV, E. Wallace and S. Singh, Autoprompt: Eliciting knowledge from language models with automatically generated prompts, preprint (2020), arXiv:2010.15980.","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"S0218001425590232BIB026","unstructured":"C. Walker, S. Strassel, J. Medero and K. Maeda, Ace 2005 multilingual training corpus (2006)."},{"key":"S0218001425590232BIB027","author":"Wang L.","year":"2025","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"S0218001425590232BIB028","unstructured":"J. White, Q. Fu, S. Hays, M. Sandborn, C. Olea, H. Gilbert, A. Elnashar, J. Spencer-Smith and D. C. Schmidt, A prompt pattern catalog to enhance prompt engineering with chatgpt, preprint (2023), arXiv:2302.11382."},{"key":"S0218001425590232BIB029","doi-asserted-by":"crossref","unstructured":"S. Wiseman, S. M. Shieber and A. M. Rush, Challenges in data-to-document generation, preprint (2017), arXiv:1707.08052.","DOI":"10.18653\/v1\/D17-1239"},{"key":"S0218001425590232BIB030","author":"Sun C.","year":"2025","journal-title":"International Journal of Pattern Recognition and Artificial Intelligence"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001425590232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T11:00:26Z","timestamp":1769770826000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218001425590232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,24]]},"references-count":30,"journal-issue":{"issue":"04","published-print":{"date-parts":[[2026,3,30]]}},"alternative-id":["10.1142\/S0218001425590232"],"URL":"https:\/\/doi.org\/10.1142\/s0218001425590232","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"value":"0218-0014","type":"print"},{"value":"1793-6381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,24]]},"article-number":"2559023"}}