{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:35:16Z","timestamp":1780500916359,"version":"3.54.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T00:00:00Z","timestamp":1736812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T00:00:00Z","timestamp":1736812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Research Project of Shaanxi Coal Geology Group Co. Ltd.","award":["SMDZ-2023CX-14"],"award-info":[{"award-number":["SMDZ-2023CX-14"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176196"],"award-info":[{"award-number":["62176196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shaanxi Provincial Water Conservancy Development Fund Project","award":["2022SLKJ-17"],"award-info":[{"award-number":["2022SLKJ-17"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s10489-024-05937-6","type":"journal-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T00:37:59Z","timestamp":1736815079000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["TableGPT: a novel table understanding method based on table recognition and large language model collaborative enhancement"],"prefix":"10.1007","volume":"55","author":[{"given":"Yi","family":"Ren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenglong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0047-8955","authenticated-orcid":false,"given":"Weibin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixuan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"TianYi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ChenHao","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"WenBo","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,14]]},"reference":[{"key":"5937_CR1","doi-asserted-by":"crossref","unstructured":"Bahrini A, Khamoshifar M, Abbasimehr H et al. ChatGPT: Applications, opportunities, and threats. 2023 Systems and Information Engineering Design Symposium (SIEDS). IEEE, 2023: 274-279","DOI":"10.1109\/SIEDS58326.2023.10137850"},{"key":"5937_CR2","unstructured":"Cui J, Li Z, Yan Y, Chen B, Yuan L (2023) Chatlaw: Open-source legal large language model with integrated external knowledge bases. arXiv preprint arXiv:2306.16092"},{"key":"5937_CR3","unstructured":"Wang H, Liu C, Xi N et al. (2023) Huatuo: Tuning llama model with chinese medical knowledge. arXiv preprint arXiv:2304.06975"},{"key":"5937_CR4","unstructured":"Xiong H, Wang S, Zhu Y et al. (2023) Doctorglm: Fine-tuning your chinese doctor is not a herculean task. arXiv preprint arXiv:2304.01097"},{"key":"5937_CR5","unstructured":"Zhao WX, Zhou K, Li J et al. (2023) A survey of large language models. arXiv preprint arXiv:2303.18223"},{"key":"5937_CR6","doi-asserted-by":"crossref","unstructured":"Du Z, Qian Y, Liu X et al. (2021) Glm: General language model pretraining with autoregressive blank infilling. arXiv preprint arXiv:2103.10360","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"5937_CR7","unstructured":"Xi Z, Chen W, Guo X et al. (2023) The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864"},{"key":"5937_CR8","unstructured":"Shi J, Shi C (2023) A Review On Table Recognition Based On Deep Learning. arXiv preprint arXiv:2312.04808"},{"key":"5937_CR9","doi-asserted-by":"crossref","unstructured":"Xue W, Yu B, Wang W et al. (2021) Tgrnet: A table graph reconstruction network for table structure recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 1295\u20131304","DOI":"10.1109\/ICCV48922.2021.00133"},{"key":"5937_CR10","doi-asserted-by":"crossref","unstructured":"Xing H, Gao F, Long R et al. (2023) LORE: Logical Location Regression Network for Table Structure Recognition. arXiv preprint arXiv:2303.03730","DOI":"10.1609\/aaai.v37i3.25402"},{"key":"5937_CR11","doi-asserted-by":"crossref","unstructured":"Qiao L, Li Z, Cheng Z, Zhang P et al. (2021) LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment. In ArXiv preprint, vol. abs\/2105.06224","DOI":"10.1007\/978-3-030-86549-8_7"},{"key":"5937_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109006","volume":"133","author":"C Ma","year":"2023","unstructured":"Ma C, Lin W, Sun L et al (2023) Robust table detection and structure recognition from heterogeneous document images. Pattern Recogn 133:109006","journal-title":"Pattern Recogn"},{"key":"5937_CR13","doi-asserted-by":"crossref","unstructured":"Lin W, Sun Z, Ma C et al. (2022) Tsrformer: Table structure recognition with transformers. Proceedings of the 30th ACM International Conference on Multimedia. 6473\u20136482","DOI":"10.1145\/3503161.3548038"},{"key":"5937_CR14","unstructured":"Guo Z, Yu Y, Lv P et al. (2022) TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers. ArXiv preprint ArXiv:2208.14687"},{"key":"5937_CR15","unstructured":"Liu H, Li X, Gong M et al. (2023) Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation. ArXiv preprint ArXiv:2303.09174"},{"key":"5937_CR16","doi-asserted-by":"crossref","unstructured":"Paliwal SS, Vishwanath D, Rahul R et al. (2019) Tablenet: Deep learning model for end-to-end table detection and tabular data extraction from scanned document images. 2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE. 128\u2013133","DOI":"10.1109\/ICDAR.2019.00029"},{"key":"5937_CR17","doi-asserted-by":"publisher","unstructured":"Schreiber S, Agne S, Wolf I, Dengel A, Ahmed S (2017) DeepDeSRT: Deep Learning for Detection and Structure Recognition of Tables in Document Images. 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan, pp. 1162\u20131167. https:\/\/doi.org\/10.1109\/ICDAR.2017.192","DOI":"10.1109\/ICDAR.2017.192"},{"key":"5937_CR18","doi-asserted-by":"publisher","unstructured":"Siddiqui SA, Fateh IA, Rizvi STR, Dengel A, Ahmed S (2019) DeepTabStR: Deep Learning based Table Structure Recognition, 2019 International Conference on Document Analysis and Recognition (ICDAR), Sydney, NSW, Australiapp. 1403\u20131409. https:\/\/doi.org\/10.1109\/ICDAR.2019.00226","DOI":"10.1109\/ICDAR.2019.00226"},{"key":"5937_CR19","doi-asserted-by":"crossref","unstructured":"Zhong X, ShafieiBavani E, Jimeno Yepes A (2020) Image-based table recognition: data, model, and evaluation. European conference on computer vision. Cham: Springer International Publishing 564\u2013580","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"5937_CR20","doi-asserted-by":"crossref","unstructured":"Nassar A, Livathinos N, Lysak M et al. (2022) Tableformer: Table structure understanding with transformers. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4614\u20134623","DOI":"10.1109\/CVPR52688.2022.00457"},{"key":"5937_CR21","doi-asserted-by":"publisher","unstructured":"Xue W, Li Q, Tao D et al. (2019) ReS2TIM: Reconstruct Syntactic Structures from Table Images. 2019 International Conference on Document Analysis and Recognition (ICDAR), Sydney, NSW, Australia, pp 749\u2013755. https:\/\/doi.org\/10.1109\/ICDAR.2019.00125","DOI":"10.1109\/ICDAR.2019.00125"},{"key":"5937_CR22","doi-asserted-by":"publisher","first-page":"108565","DOI":"10.1016\/j.patcog.2022.108565","volume":"126","author":"Z Zhang","year":"2022","unstructured":"Zhang Z, Zhang J, Du J et al (2022) Split, embed and merge: An accurate table structure recognizer. Pattern Recogn 126:108565","journal-title":"Pattern Recogn"},{"key":"5937_CR23","doi-asserted-by":"publisher","first-page":"110279","DOI":"10.1016\/j.patcog.2024.110279","volume":"149","author":"Z Zhang","year":"2024","unstructured":"Zhang Z, Hu P, Ma J et al (2024) SEMv2: Table Separation Line Detection Based on Instance Segmentation. Pattern Recogn 149:110279","journal-title":"Pattern Recogn"},{"key":"5937_CR24","doi-asserted-by":"crossref","unstructured":"Prasad PD, Gadpal A, Kapadni K et al. (2020) CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp 572\u2013573","DOI":"10.1109\/CVPRW50498.2020.00294"},{"key":"5937_CR25","doi-asserted-by":"crossref","unstructured":"Siddiqui SA, Fateh IA, Rizvi STR et al. (2019) Deeptabstr: Deep learning based table structure recognition. In *Proceedings of the 2019 International Conference on Document Analysis and Recognition (ICDAR)*, IEEE pp 1403\u20131409","DOI":"10.1109\/ICDAR.2019.00226"},{"key":"5937_CR26","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P et al. (2017) Mask R-CNN. In *Proceedings of the IEEE International Conference on Computer Vision* 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"5937_CR27","doi-asserted-by":"crossref","unstructured":"Jimeno Yepes A, Zhong P, Burdick D (2021) ICDAR 2021 competition on scientific literature parsing[C]\/\/Document Analysis and Recognition\u2013ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part IV 16. Springer International Publishing 605-617","DOI":"10.1007\/978-3-030-86337-1_40"},{"key":"5937_CR28","unstructured":"Li C, Guo R, Zhou J et al. (2022) PP-StructureV2: A Stronger Document Analysis System. arXiv preprint arXiv:2210.05391"},{"key":"5937_CR29","doi-asserted-by":"crossref","unstructured":"Jain A, Paliwal S, Sharma M et al. (2022) TSR-DSAW: Table Structure Recognition via Deep Spatial Association of Words. arXiv preprint arXiv:2203.06873","DOI":"10.14428\/esann\/2021.ES2021-109"},{"key":"5937_CR30","doi-asserted-by":"crossref","unstructured":"Ly NT, Takasu A, Nguyen P et al. (2023) Rethinking Image-Based Table Recognition Using Weakly Supervised Methods. arXiv preprint arXiv:2303.07641","DOI":"10.5220\/0011682600003411"},{"key":"5937_CR31","unstructured":"Radford A, Narasimhan K, Salimans T et al. (2018) Improving language understanding by generative pre-training"},{"key":"5937_CR32","unstructured":"Vaswani A, Shazeer N, Parmar N et al. (2017) Attention is all you need. Advances in neural information processing systems 30"},{"issue":"8","key":"5937_CR33","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford A, Wu J, Child R et al (2019) Language models are unsupervised multitask learners. OpenAI blog 1(8):9","journal-title":"OpenAI blog"},{"key":"5937_CR34","unstructured":"Mahabadi RK, Ruder S, Dehghani M et al. (2021) Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks. arXiv preprint arXiv:2106.04489"},{"key":"5937_CR35","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"key":"5937_CR36","unstructured":"R. OpenAI (2023) Gpt-4 technical report. arxiv 2303.08774. View in Article 2: 13"},{"key":"5937_CR37","first-page":"2","volume":"1","author":"X Wang","year":"2022","unstructured":"Wang X, Xie L, Dong C et al (2022) Realesrgan: Training real-world blind super-resolution with pure synthetic data supplementary material. Computer Vision Foundation open access 1:2","journal-title":"Computer Vision Foundation open access"},{"key":"5937_CR38","doi-asserted-by":"crossref","unstructured":"Ly NT, Takasu A (2023) An End-to-End Multi-Task Learning Model for Image-based Table Recognition. arXiv preprint arXiv:2303.08648","DOI":"10.5220\/0011685000003417"},{"key":"5937_CR39","unstructured":"J Zhong Academic Value of Web-Based Collaborative Encyclopedia: A Corpus-Informed Discourse Analysis of Baidu Encyclopedia and Chinese Wikipedia"},{"key":"5937_CR40","unstructured":"Zeng A, Liu X, Du Z et al. (2022) Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414"},{"key":"5937_CR41","unstructured":"Hu EJ, Shen Y, Wallis P et al. (2021) Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685"},{"key":"5937_CR42","unstructured":"Bai J, Bai S, Yang S et al. (2023) Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966"},{"key":"5937_CR43","unstructured":"Bai J, Bai S, Chu Y et al. (2023) Qwen technical report. arXiv preprint arXiv:2309.16609"},{"key":"5937_CR44","doi-asserted-by":"crossref","unstructured":"Zhong X, ShafieiBavani E, Jimeno Yepes A (2020) Image-based table recognition: data, model, and evaluation. European conference on computer vision. Cham: Springer International Publishing 564\u2013580.","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"5937_CR45","doi-asserted-by":"crossref","unstructured":"Jimeno Yepes A, Zhong P, Burdick D (2021) ICDAR 2021 competition on scientific literature parsing. Document Analysis and Recognition\u2013ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part IV 16. Springer International Publishing 605-617","DOI":"10.1007\/978-3-030-86337-1_40"},{"key":"5937_CR46","unstructured":"Kim2091 (2021) 4X-UltraSharp: A High-Quality Upscaler for Stable Diffusion. Available: https:\/\/civitai.com\/models\/116225\/4x-ultrasharp. [Accessed: Oct. 27, 2021]"},{"key":"5937_CR47","doi-asserted-by":"crossref","unstructured":"Wang X, Yu K, Wu S et al. (2018) Esrgan: Enhanced super-resolution generative adversarial networks. Proceedings of the European conference on computer vision (ECCV) workshops","DOI":"10.1007\/978-3-030-11021-5_5"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05937-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05937-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05937-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T17:20:31Z","timestamp":1740244831000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05937-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,14]]},"references-count":47,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["5937"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05937-6","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,14]]},"assertion":[{"value":"12 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}}],"article-number":"311"}}