{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T23:57:44Z","timestamp":1777939064005,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tkde.2026.3673401","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:39:05Z","timestamp":1773347945000},"page":"4048-4061","source":"Crossref","is-referenced-by-count":0,"title":["Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science With Table-Specific Pretraining"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1627-8341","authenticated-orcid":false,"given":"Yazheng","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Information Systems and Management Engineering, The University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2930-0654","authenticated-orcid":false,"given":"Yuqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Information Systems and Management Engineering, The University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3985-1573","authenticated-orcid":false,"given":"Yaxuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7126-5847","authenticated-orcid":false,"given":"Sankalok","family":"Sen","sequence":"additional","affiliation":[{"name":"Department of Information Systems and Management Engineering, The University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Information Systems and Management Engineering, The University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2331-8698","authenticated-orcid":false,"given":"Lin","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Information Systems and Management Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4608-5778","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Information Systems and Management Engineering, The University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"991","article-title":"Enhancing financial table and text question answering with tabular graph and numerical reasoning","volume-title":"Proc. 2nd Conf. Asia-Pacific Chapter Assoc. Comput. Linguistics 12th Int. Joint Conf. Natural Lang. Process.","author":"Nararatwong","year":"2022"},{"key":"ref2","first-page":"9471","article-title":"AnaMeta: A table understanding dataset of field metadata knowledge shared by multi-dimensional data analysis tasks","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"He","year":"2023"},{"key":"ref3","first-page":"1157","article-title":"QTSumm: Query-focused summarization over tabular data","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Zhao","year":"2023"},{"key":"ref4","first-page":"14836","article-title":"Generative table pre-training empowers models for tabular prediction","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Zhang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.179"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.335"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.17"},{"key":"ref8","first-page":"43181","article-title":"XTab: Cross-table pretraining for tabular transformers","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Zhu","year":"2023"},{"key":"ref9","article-title":"TABLET: Learning from instructions for tabular data","author":"Slack","year":"2023"},{"key":"ref10","first-page":"24991","article-title":"On embeddings for numerical features in tabular deep learning","volume":"35","author":"Gorishniy","year":"2022","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref11","first-page":"2902","article-title":"TransTab: Learning transferable tabular transformers across tables","volume":"35","author":"Wang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref12","article-title":"PTab: Using the pre-trained language model for modeling tabular data","author":"Liu","year":"2022"},{"key":"ref13","first-page":"5549","article-title":"TabLLM: Few-shot classification of tabular data with large language models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Hegselmann","year":"2023"},{"key":"ref14","article-title":"Chain-of-Table: Evolving tables in the reasoning chain for table understanding","volume-title":"Proc. 12th Int. Conf. Learn. Representation","author":"Wang","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3654979"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00446"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.78"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3542700.3542709"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.89"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.745"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref23","article-title":"Neural oblivious decision ensembles for deep learning on tabular data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Popov","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","article-title":"TabTransformer: Tabular data modeling using contextual embeddings","author":"Huang","year":"2020"},{"key":"ref26","first-page":"18932","article-title":"Revisiting deep learning models for tabular data","volume":"34","author":"Gorishniy","year":"2021","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref27","article-title":"UniTabE: A universal pretraining protocol for tabular foundation model in data science","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Yang","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.745"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467434"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.40"},{"key":"ref31","article-title":"TabPFN: A transformer that solves small tabular classification problems in a second","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Hollmann","year":"2023"},{"key":"ref32","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.331"},{"key":"ref34","article-title":"arXiVeri: Automatic table verification with GPT","volume-title":"Proc. NeurIPS AI Sci. Workshop","author":"Shin","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.260"},{"key":"ref37","article-title":"Data engineering for scaling language models to 128 k context","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Fu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3799830.3799835"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0768"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0037"},{"key":"ref41","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref42","first-page":"55006","article-title":"LIMA: Less is more for alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhou","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11503382\/11433012.pdf?arnumber=11433012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T05:02:19Z","timestamp":1777698139000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":43,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2026.3673401","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}