{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T15:07:58Z","timestamp":1774883278273,"version":"3.50.1"},"reference-count":169,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:00:00Z","timestamp":1768867200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:00:00Z","timestamp":1768867200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24A201401"],"award-info":[{"award-number":["U24A201401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24A201401"],"award-info":[{"award-number":["U24A201401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24A201401"],"award-info":[{"award-number":["U24A201401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24A201401"],"award-info":[{"award-number":["U24A201401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24A201401"],"award-info":[{"award-number":["U24A201401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24A201401"],"award-info":[{"award-number":["U24A201401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24A201401"],"award-info":[{"award-number":["U24A201401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24A201401"],"award-info":[{"award-number":["U24A201401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24A201401"],"award-info":[{"award-number":["U24A201401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s11280-025-01399-z","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T04:15:45Z","timestamp":1768882545000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward real-world Table Agents: capabilities, workflows, and design principles for LLM-based table intelligence"],"prefix":"10.1007","volume":"29","author":[{"given":"Jiaming","family":"Tian","sequence":"first","affiliation":[]},{"given":"Liyao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Wentao","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Haobo","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Lingxin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Lihua","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Zujie","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Junbo","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"key":"1399_CR1","unstructured":"Hwang, Y., Lim, J., Lee, Y.-J., Choi, H.-J.: Augmentation for context in financial numerical reasoning over textual and tabular data with large-scale language model. In: NeurIPS 2023 Second Table Representation Learning Workshop (2023)"},{"key":"1399_CR2","doi-asserted-by":"crossref","unstructured":"Shi, W., Xu, R., Zhuang, Y., Yu, Y., Zhang, J., Wu, H., Zhu, Y., Ho, J.C., Yang, C., Wang, M.D.: Ehragent: Code empowers large language models for few-shot complex tabular reasoning on electronic health records. In: ICLR 2024 Workshop on Large Language Model (LLM) Agents (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.1245"},{"key":"1399_CR3","doi-asserted-by":"crossref","unstructured":"Musumeci, E., Brienza, M., Suriani, V., Nardi, D., Bloisi, D.D.: Llm based multi-agent generation of semi-structured documents from semantic templates in the public administration domain. In: International Conference on Human-Computer Interaction, pp. 98\u2013117 (2024)","DOI":"10.1007\/978-3-031-60615-1_7"},{"key":"1399_CR4","doi-asserted-by":"crossref","unstructured":"Do, T., Gurung, B.D.S., Aryal, S., Khanal, A., Chataut, S., Gadhamshetty, V., Lushbough, C., Gnimpieba, E.Z.: Utilizing xgboost for the prediction of material corrosion rates from embedded tabular data using large language model. In: 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 4497\u20134499 (2023)","DOI":"10.1109\/BIBM58861.2023.10385544"},{"key":"1399_CR5","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al.: Gpt-4 technical report. (2023). arXiv:2303.08774"},{"key":"1399_CR6","doi-asserted-by":"crossref","unstructured":"Yu, T., Zhang, R., Yang, K., Yasunaga, M., Wang, D., Li, Z., Ma, J., Li, I., Yao, Q., Roman, S., et al.: Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018)","DOI":"10.18653\/v1\/D18-1425"},{"key":"1399_CR7","doi-asserted-by":"crossref","unstructured":"Pasupat, P., Liang, P.: Compositional semantic parsing on semi-structured tables. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 1470\u20131480 (2015)","DOI":"10.3115\/v1\/P15-1142"},{"key":"1399_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Yuan, Y., Zhang, Z., Zheng, Y., Liu, J., Ni, F., Jianye, H.: Sheetagent: A generalist agent for spreadsheet reasoning and manipulation via large language models. In: ICML 2024 Workshop on LLMs and Cognition (2024)","DOI":"10.1145\/3696410.3714962"},{"issue":"8","key":"1399_CR9","doi-asserted-by":"publisher","first-page":"1981","DOI":"10.14778\/3659437.3659452","volume":"17","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Henkel, J., Floratou, A., Cahoon, J., Deep, S., Patel, J.M.: Reactable: enhancing react for table question answering. Proceed. VLDB Endowment 17(8), 1981\u20131994 (2024)","journal-title":"Proceed. VLDB Endowment"},{"issue":"6","key":"1399_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1","volume":"18","author":"L Wang","year":"2024","unstructured":"Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., Zhao, W.X., Wei, Z., Wen, J.: A survey on large language model based autonomous agents. Front. Comput. Sci. 18(6), 186345 (2024). https:\/\/doi.org\/10.1007\/s11704-024-40231-1","journal-title":"Front. Comput. Sci."},{"issue":"2","key":"1399_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0","volume":"68","author":"Z Xi","year":"2025","unstructured":"Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al.: The rise and potential of large language model based agents: A survey. Sci. China Inf. Sci. 68(2), 121101 (2025)","journal-title":"Sci. China Inf. Sci."},{"key":"1399_CR12","unstructured":"Tian, Y., Zhao, J., Dong, H., Xiong, J., Xia, S., Zhou, M., Lin, Y., Cambronero, J., He, Y., Han, S., et al.: Spreadsheetllm: Encoding spreadsheets for large language models. (2024). arXiv:2407.09025"},{"key":"1399_CR13","unstructured":"Patnaik, S., Changwal, H., Aggarwal, M., Bhatia, S., Kumar, Y., Krishnamurthy, B.: Cabinet: Content relevance-based noise reduction for table question answering. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"1399_CR14","doi-asserted-by":"crossref","unstructured":"Zheng, M., Feng, X., Si, Q., She, Q., Lin, Z., Jiang, W., Wang, W.: Multimodal table understanding. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 9102\u20139124 (2024)","DOI":"10.18653\/v1\/2024.acl-long.493"},{"key":"1399_CR15","unstructured":"Zhao, W., Feng, H., Liu, Q., Tang, J., Wei, S., Wu, B., Liao, L., Ye, Y., Liu, H., Li, H., et al.: Tabpedia: Towards comprehensive visual table understanding with concept synergy. (2024). arXiv:2406.01326"},{"key":"1399_CR16","doi-asserted-by":"crossref","unstructured":"Jin, R., Li, Y., Qi, G., Hu, N., Li, Y.-F., Chen, J., Wang, J., Chen, Y., Min, D., Bi, S.: Hegta: Leveraging heterogeneous graph-enhanced large language models for few-shot complex table understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 24294\u201324302 (2025)","DOI":"10.1609\/aaai.v39i23.34606"},{"key":"1399_CR17","unstructured":"Su, A., Wang, A., Ye, C., Zhou, C., Zhang, G., Zhu, G., Wang, H., Xu, H., Chen, H., Li, H., Lan, H., Tian, J., Yuan, J., Zhao, J., Zhou, J., Shou, K., Zha, L., Long, L., Li, L., Wu, P., Zhang, Q., Huang, Q., Yang, S., Zhang, T., Ye, W., Zhu, W., Hu, X., Gu, X., Sun, X., Li, X., Yang, Y., Xiao, Z.: TableGPT2: A Large Multimodal Model with Tabular Data Integration (2024). arXiv:2411.02059"},{"key":"1399_CR18","doi-asserted-by":"crossref","unstructured":"Guo, Y., Yang, Y., Zhang, Y., Wang, Y., Wang, Y.: Dictllm: Harnessing key-value data structures with large language models for enhanced medical diagnostics. In: Findings of the Association for Computational Linguistics ACL 2024, pp. 10231\u201310241 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.609"},{"key":"1399_CR19","unstructured":"Hu, X., Zhao, Z., Wei, S., Chai, Z., Ma, Q., Wang, G., Wang, X., Su, J., Xu, J., Zhu, M., et al.: Infiagent-dabench: evaluating agents on data analysis tasks. In: Proceedings of the 41st International Conference on Machine Learning, pp. 19544\u201319572 (2024)"},{"key":"1399_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, J., Shen, Z., Srinivasan, B., Wang, S., Rangwala, H., Karypis, G.: Nameguess: Column name expansion for tabular data. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 13276\u201313290 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.820"},{"key":"1399_CR21","unstructured":"Mao, Q., Liu, Q., Li, Z., Cheng, M., Zhang, Z., Li, R.: Potable: Programming standardly on table-based reasoning like a human analyst. (2024). arXiv:2412.04272"},{"key":"1399_CR22","doi-asserted-by":"crossref","unstructured":"Pourreza, M., Rafiei, D.: Dts-sql: Decomposed text-to-sql with small large language models. In: EMNLP (Findings) (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.481"},{"key":"1399_CR23","doi-asserted-by":"crossref","unstructured":"Pourreza, M., Rafiei, D.: Din-sql: Decomposed in-context learning of text-to-sql with self-correction. Adv. Neural Inf. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-1577"},{"key":"1399_CR24","unstructured":"Wang, B., Ren, C., Yang, J., Liang, X., Bai, J., Chai, L., Yan, Z., Zhang, Q.-W., Yin, D., Sun, X., et al.: Mac-sql: A multi-agent collaborative framework for text-to-sql. In: COLING (2025)"},{"key":"1399_CR25","doi-asserted-by":"crossref","unstructured":"Kothyari, M., Dhingra, D., Sarawagi, S., Chakrabarti, S.: Crush4sql: Collective retrieval using schema hallucination for text2sql. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 14054\u201314066 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.868"},{"key":"1399_CR26","unstructured":"Zhang, X., Wang, D., Dou, L., Zhu, Q., Che, W.: Multi-hop table retrieval for open-domain text-to-sql. (2024). arXiv:2402.10666"},{"key":"1399_CR27","unstructured":"Dom\u00ednguez, J.M., Err\u00e1zuriz, B., Daher, P.: Blar-sql: Faster, stronger, smaller nl2sql. (2024). arXiv:2401.02997"},{"key":"1399_CR28","unstructured":"Wuzhenghong, W., Yongpan, Z., Su, P., Yuwei, S., Pengwei, L., Cheng, D.: Lr-sql: A supervised fine-tuning method for text2sql tasks under low-resource scenarios. (2024). arXiv:2410.11457"},{"key":"1399_CR29","unstructured":"Kong, K., Zhang, J., Shen, Z., Srinivasan, B., Lei, C., Faloutsos, C., Rangwala, H., Karypis, G.: Opentab: Advancing large language models as open-domain table reasoners. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"1399_CR30","doi-asserted-by":"crossref","unstructured":"Ren, T., Fan, Y., He, Z., Huang, R., Dai, J., Huang, C., Jing, Y., Zhang, K., Yang, Y., Wang, X.S.: Purple: Making a large language model a better sql writer. In: 2024 IEEE 40th International Conference on Data Engineering (ICDE), pp. 15\u201328 (2024). IEEE","DOI":"10.1109\/ICDE60146.2024.00009"},{"key":"1399_CR31","doi-asserted-by":"publisher","first-page":"74899","DOI":"10.52202\/079017-2382","volume":"37","author":"S-A Chen","year":"2024","unstructured":"Chen, S.-A., Miculicich, L., Eisenschlos, J., Wang, Z., Wang, Z., Chen, Y., Fujii, Y., Lin, H.-T., Lee, C.-Y., Pfister, T.: Tablerag: Million-token table understanding with language models. Adv. Neural. Inf. Process. Syst. 37, 74899\u201374921 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1399_CR32","doi-asserted-by":"crossref","unstructured":"Lei, W., Wang, W., Ma, Z., Gan, T., Lu, W., Kan, M.-Y., Chua, T.-S.: Re-examining the role of schema linking in text-to-sql. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6943\u20136954 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.564"},{"key":"1399_CR33","unstructured":"Volvovsky, S., Marcassa, M., Panbiharwala, M.: Dfin-sql: Integrating focused schema with din-sql for superior accuracy in large-scale databases. (2024). arXiv:2403.00872"},{"key":"1399_CR34","unstructured":"Zha, L., Zhou, J., Li, L., Wang, R., Huang, Q., Yang, S., Yuan, J., Su, C., Li, X., Su, A., et al.: Tablegpt: Towards unifying tables, nature language and commands into one gpt. (2023). arXiv:2307.08674"},{"key":"1399_CR35","unstructured":"Gu, Y., Zheng, B., Gou, B., Zhang, K., Chang, C., Srivastava, S., Xie, Y., Qi, P., Sun, H., Su, Y.: Is your llm secretly a world model of the internet? model-based planning for web agents. (2024). arXiv:2411.06559"},{"key":"1399_CR36","unstructured":"Wang, Z., Zhang, H., Li, C.-L., Eisenschlos, J.M., Perot, V., Wang, Z., Miculicich, L., Fujii, Y., Shang, J., Lee, C.-Y., et al.: Chain-of-table: Evolving tables in the reasoning chain for table understanding. In: ICLR (2024)"},{"key":"1399_CR37","doi-asserted-by":"crossref","unstructured":"Lou, Y., Lei, C., Qin, X., Wang, Z., Faloutsos, C., Anubhai, R., Rangwala, H.: Datalore: Can a large language model find all lost scrolls in a data repository? In: 2024 IEEE 40th International Conference on Data Engineering (ICDE), pp. 5170\u20135176 (2024). IEEE","DOI":"10.1109\/ICDE60146.2024.00388"},{"key":"1399_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, F., Lei, W., Huang, Y., Wang, C., Zhang, S., Lv, J., Feng, F., Chua, T.-S.: Tat-qa: A question answering benchmark on a hybrid of tabular and textual content in finance. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (2021). Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.acl-long.254"},{"key":"1399_CR39","doi-asserted-by":"crossref","unstructured":"Chen, Z., Chen, W., Smiley, C., Shah, S., Borova, I., Langdon, D., Moussa, R., Beane, M., Huang, T.-H., Routledge, B.R., et al.: Finqa: A dataset of numerical reasoning over financial data. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3697\u20133711 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"1399_CR40","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, S., Smiley, C., Ma, Z., Shah, S., Wang, W.Y.: Convfinqa: Exploring the chain of numerical reasoning in conversational finance question answering. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 6279\u20136292 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.421"},{"key":"1399_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Li, Y., Li, C., Zhang, R.: Multihiertt: Numerical reasoning over multi hierarchical tabular and textual data. In: 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022, pp. 6588\u20136600 (2022). Association for Computational Linguistics (ACL)","DOI":"10.18653\/v1\/2022.acl-long.454"},{"key":"1399_CR42","doi-asserted-by":"crossref","unstructured":"Theuma, A., Shareghi, E.: Equipping language models with tool use capability for tabular data analysis in finance. In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 90\u2013103 (2024)","DOI":"10.18653\/v1\/2024.eacl-short.10"},{"key":"1399_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, C., Mao, Y., Fan, Y., Mi, Y., Gao, Y., Chen, L., Lou, D., Lin, J.: Finsql: Model-agnostic llms-based text-to-sql framework for financial analysis. In: Companion of the 2024 International Conference on Management of Data, pp. 93\u2013105 (2024)","DOI":"10.1145\/3626246.3653375"},{"key":"1399_CR44","doi-asserted-by":"crossref","unstructured":"Chen, Y., Gu, S., He, Z.: Fato-sql: a comprehensive framework for high-performance text-to-sql task. In: International Conference on Optics, Electronics, and Communication Engineering (OECE 2024), vol. 13395, pp. 841\u2013848 (2024)","DOI":"10.1117\/12.3049621"},{"key":"1399_CR45","unstructured":"Li, H., Su, J., Chen, Y., Li, Q., ZHANG, Z.-X.: Sheetcopilot: Bringing software productivity to the next level through large language models. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"1399_CR46","unstructured":"Zhang, W., Shen, Y., Lu, W., Zhuang, Y.: Data-copilot: Bridging billions of data and humans with autonomous workflow. In: ICLR 2024 Workshop on Large Language Model (LLM) Agents (2024)"},{"key":"1399_CR47","unstructured":"Xue, S., Jiang, C., Shi, W., Cheng, F., Chen, K., Yang, H., Zhang, Z., He, J., Zhang, H., Wei, G., et al.: Db-gpt: Empowering database interactions with private large language models. (2023). arXiv:2312.17449"},{"key":"1399_CR48","doi-asserted-by":"crossref","unstructured":"Wang, C., Thompson, J., Lee, B.: Data formulator: Ai-powered concept-driven visualization authoring. IEEE Transactions on Visualization and Computer Graphics (2023)","DOI":"10.1109\/TVCG.2023.3326585"},{"key":"1399_CR49","unstructured":"Wang, C., Lee, B., Drucker, S., Marshall, D., Gao, J.: Data formulator 2: Iteratively creating rich visualizations with ai. (2024). arXiv:2408.16119"},{"key":"1399_CR50","unstructured":"Xie, W., Wu, G., Zhou, B.: Mag-sql: Multi-agent generative approach with soft schema linking and iterative sub-sql refinement for text-to-sql. (2024). arXiv:2408.07930"},{"key":"1399_CR51","unstructured":"Talaei, S., Pourreza, M., Chang, Y.-C., Mirhoseini, A., Saberi, A.: Chess: Contextual harnessing for efficient sql synthesis. (2024). arXiv:2405.16755"},{"key":"1399_CR52","doi-asserted-by":"crossref","unstructured":"Askari, A., Poelitz, C., Tang, X.: Magic: Generating self-correction guideline for in-context text-to-sql. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 23433\u201323441 (2025)","DOI":"10.1609\/aaai.v39i22.34511"},{"issue":"3","key":"1399_CR53","first-page":"1","volume":"3","author":"X Xie","year":"2025","unstructured":"Xie, X., Xu, G., Zhao, L., Guo, R.: Opensearch-sql: Enhancing text-to-sql with dynamic few-shot and consistency alignment. Proceed. ACM Manag. Data 3(3), 1\u201324 (2025)","journal-title":"Proceed. ACM Manag. Data"},{"issue":"9","key":"1399_CR54","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40330-z","volume":"19","author":"X Zhang","year":"2025","unstructured":"Zhang, X., Wang, D., Dou, L., Zhu, Q., Che, W.: A survey of table reasoning with large language models. Front. Comput. Sci. 19(9), 199348 (2025). https:\/\/doi.org\/10.1007\/s11704-024-40330-z","journal-title":"Front. Comput. Sci."},{"key":"1399_CR55","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Nan, L., Qi, Z., Zhang, R., Radev, D.: Reastap: Injecting table reasoning skills during pre-training via synthetic reasoning examples. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 9006\u20139018 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.615"},{"key":"1399_CR56","unstructured":"Chen, W., Wang, H., Chen, J., Zhang, Y., Wang, H., Li, S., Zhou, X., Wang, W.Y.: Tabfact: A large-scale dataset for table-based fact verification. (2019). arXiv:1909.02164"},{"key":"1399_CR57","doi-asserted-by":"crossref","unstructured":"Wu, L., Wang, K., Nie, K., Guo, S., Gao, C., Wang, Z., Li, S.: Tfgin: Tight-fitting graph inference network for table-based fact verification. ACM Transactions on Information Systems (2025)","DOI":"10.1145\/3734520"},{"key":"1399_CR58","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1162\/tacl_a_00446","volume":"10","author":"L Nan","year":"2022","unstructured":"Nan, L., Hsieh, C., Mao, Z., Lin, X.V., Verma, N., Zhang, R., Kry\u015bci\u0144ski, W., Schoelkopf, H., Kong, R., Tang, X., et al.: Fetaqa: Free-form table question answering. Trans. Assoc. Computat. Linguistics 10, 35\u201349 (2022)","journal-title":"Trans. Assoc. Computat. Linguistics"},{"key":"1399_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, T., Yue, X., Li, Y., Sun, H.: Tablellama: Towards open large generalist models for tables. In: NAACL-HLT (2024)","DOI":"10.18653\/v1\/2024.naacl-long.335"},{"key":"1399_CR60","doi-asserted-by":"crossref","unstructured":"Chen, W., Zha, H., Chen, Z., Xiong, W., Wang, H., Wang, W.Y.: Hybridqa: A dataset of multi-hop question answering over tabular and textual data. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1026\u20131036 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.91"},{"key":"1399_CR61","doi-asserted-by":"crossref","unstructured":"Weng, L., Tang, Y., Feng, Y., Chang, Z., Chen, R., Feng, H., Hou, C., Huang, D., Li, Y., Rao, H., et al.: Datalab: A unified platform for llm-powered business intelligence. In: 2025 IEEE 41st International Conference on Data Engineering (ICDE), pp. 4346\u20134359 (2025). IEEE","DOI":"10.1109\/ICDE65448.2025.00326"},{"key":"1399_CR62","doi-asserted-by":"crossref","unstructured":"Wang, H., Hu, K., Dong, H., Gao, L.: Doctabqa: Answering questions from long documents using tables. In: International Conference on Document Analysis and Recognition, pp. 470\u2013487 (2024)","DOI":"10.1007\/978-3-031-70533-5_27"},{"key":"1399_CR63","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Dong, H., Wang, Z., Jia, R., Guo, J., Gao, Y., Han, S., Lou, J.-G., Zhang, D.: Hitab: A hierarchical table dataset for question answering and natural language generation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1094\u20131110 (2022)","DOI":"10.18653\/v1\/2022.acl-long.78"},{"key":"1399_CR64","unstructured":"Li, J., Hui, B., Qu, G., Yang, J., Li, B., Li, B., Wang, B., Qin, B., Geng, R., Huo, N., et al.: Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"1399_CR65","unstructured":"Qiu, Z., Peng, Y., He, G., Yuan, B., Wang, C.: Tqa-bench: Evaluating llms for multi-table question answering with scalable context and symbolic extension. (2024). arXiv:2411.19504"},{"key":"1399_CR66","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Vaughan, A., et al.: The llama 3 herd of models. (2024). arXiv:2407.21783"},{"key":"1399_CR67","unstructured":"Team, Q.: Qwen3 (2025). https:\/\/qwenlm.github.io\/blog\/qwen3\/"},{"key":"1399_CR68","unstructured":"Yang, A., Yu, B., Li, C., Liu, D., Huang, F., Huang, H., Jiang, J., Tu, J., Zhang, J., Zhou, J., et al.: Qwen2. 5-1m technical report. (2025). arXiv:2501.15383"},{"key":"1399_CR69","unstructured":"Meta AI: The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation. Accessed: 2025-04-21 (2025). https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/"},{"key":"1399_CR70","volume-title":"Database System Concepts","author":"A Silberschatz","year":"2020","unstructured":"Silberschatz, A., Korth, H.F., Sudarshan, S.: Database System Concepts, 7th edn. McGraw-Hill, New York (2020)","edition":"7"},{"key":"1399_CR71","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhao, Z., Birke, R., Chen, L.Y.: Permutation-invariant tabular data synthesis. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 5855\u20135864 (2022)","DOI":"10.1109\/BigData55660.2022.10020639"},{"key":"1399_CR72","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: Enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"1399_CR73","unstructured":"Borisov, V., Leemann, T., Se\u00dfler, K., Haug, J., Pawelczyk, M., Kasneci, G.: Deep neural networks and tabular data: A survey. IEEE Transactions on Neural Networks and Learning Systems (2022)"},{"key":"1399_CR74","unstructured":"Kaddour, J., Harris, J., Mozes, M., Bradley, H., Raileanu, R., McHardy, R.: Challenges and applications of large language models. (2023). arXiv:2307.10169"},{"key":"1399_CR75","unstructured":"Biswal, A., Patel, L., Jha, S., Kamsetty, A., Liu, S., Gonzalez, J.E., Guestrin, C., Zaharia, M.: Text2sql is not enough: Unifying ai and databases with tag. (2024). arXiv:2408.14717"},{"key":"1399_CR76","unstructured":"Fang, X., Xu, W., Tan, F.A., Hu, Z., Zhang, J., Qi, Y., Sengamedu, S.H., Faloutsos, C.: Large language models (llms) on tabular data: Prediction, generation, and understanding-a survey. Transactions on Machine Learning Research (2024)"},{"key":"1399_CR77","doi-asserted-by":"crossref","unstructured":"Sui, Y., Zhou, M., Zhou, M., Han, S., Zhang, D.: Table meets llm: Can large language models understand structured table data? a benchmark and empirical study. In: Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pp. 645\u2013654 (2024)","DOI":"10.1145\/3616855.3635752"},{"key":"1399_CR78","unstructured":"Singha, A., Cambronero, J., Gulwani, S., Le, V., Parnin, C.: Tabular representation, noisy operators, and impacts on table structure understanding tasks in llms. In: NeurIPS 2023 Second Table Representation Learning Workshop (2023)"},{"key":"1399_CR79","unstructured":"Wang, Z., Gao, C., Xiao, C., Sun, J.: Meditab: scaling medical tabular data predictors via data consolidation, enrichment, and refinement. In: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, pp. 6062\u20136070 (2024)"},{"key":"1399_CR80","unstructured":"Sui, Y., Zhou, M., Zhou, M., Han, S., Zhang, D.: Evaluating and enhancing structural understanding capabilities of large language models on tables via input designs. (2023). arXiv:2305.13062"},{"key":"1399_CR81","unstructured":"Jaitly, S., Shah, T., Shugani, A., Grewal, R.S.: Towards better serialization of tabular data for few-shot classification. (2023). arXiv:2312.12464"},{"key":"1399_CR82","doi-asserted-by":"crossref","unstructured":"Yu, B., Fu, C., Yu, H., Huang, F., Li, Y.: Unified language representation for question answering over text, tables, and images. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 4756\u20134765 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.292"},{"key":"1399_CR83","doi-asserted-by":"crossref","unstructured":"Gong, H., Sun, Y., Feng, X., Qin, B., Bi, W., Liu, X., Liu, T.: Tablegpt: Few-shot table-to-text generation with table structure reconstruction and content matching. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 1978\u20131988 (2020)","DOI":"10.18653\/v1\/2020.coling-main.179"},{"key":"1399_CR84","unstructured":"Zhang, X., Wang, D., Dou, L., Wang, B., Wu, D., Zhu, Q., Che, W.: Flextaf: Enhancing table reasoning with flexible tabular formats. (2024). arXiv:2408.08841"},{"key":"1399_CR85","doi-asserted-by":"crossref","unstructured":"Deng, N., Sun, Z., He, R., Sikka, A., Chen, Y., Ma, L., Zhang, Y., Mihalcea, R.: Tables as texts or images: Evaluating the table reasoning ability of llms and mllms. In: Findings of the Association for Computational Linguistics ACL 2024, pp. 407\u2013426 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.23"},{"key":"1399_CR86","doi-asserted-by":"crossref","unstructured":"Liu, T., Wang, F., Chen, M.: Rethinking tabular data understanding with large language models. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 450\u2013482 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.26"},{"key":"1399_CR87","unstructured":"Ling, J., Qi, Y., Huang, T., Zhou, S., Huang, Y., Yang, J., Song, Z., Zhou, Y., Yang, Y., Shen, H.T., et al.: Table2latex-rl: High-fidelity latex code generation from table images via reinforced multimodal language models. (2025). arXiv:2509.17589"},{"key":"1399_CR88","unstructured":"OpenAI: GPT-4V(ision) System Card. OpenAI (2023)"},{"key":"1399_CR89","unstructured":"Team, G., Anil, R., Borgeaud, S., Wu, Y., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A.M., Hauth, A., et al.: Gemini: a family of highly capable multimodal models. (2023). arXiv:2312.11805"},{"key":"1399_CR90","unstructured":"Yang, Z., Li, L., Lin, K., Wang, J., Lin, C.-C., Liu, Z., Wang, L.: The dawn of lmms: Preliminary explorations with gpt-4v (ision). 9(1), 1 (2023). arXiv:2309.17421"},{"key":"1399_CR91","unstructured":"Lu, H., Liu, W., Zhang, B., Wang, B., Dong, K., Liu, B., Sun, J., Ren, T., Li, Z., Sun, Y., et al.: Deepseek-vl: towards real-world vision-language understanding. (2024). arXiv:2403.05525"},{"key":"1399_CR92","unstructured":"Zhang, G., Du, X., Chen, B., Liang, Y., Luo, T., Zheng, T., Zhu, K., Cheng, Y., Xu, C., Guo, S., et al.: Cmmmu: A chinese massive multi-discipline multimodal understanding benchmark. (2024). arXiv:2401.11944"},{"key":"1399_CR93","doi-asserted-by":"crossref","unstructured":"Hu, A., Shi, Y., Xu, H., Ye, J., Ye, Q., Yan, M., Li, C., Qian, Q., Zhang, J., Huang, F.: mplug-paperowl: Scientific diagram analysis with the multimodal large language model. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 6929\u20136938 (2024)","DOI":"10.1145\/3664647.3681294"},{"key":"1399_CR94","doi-asserted-by":"crossref","unstructured":"Kim, Y., Yim, M., Song, K.Y.: Tablevqa-bench: A visual question answering benchmark on multiple table domains. (2024). arXiv:2404.19205","DOI":"10.18653\/v1\/2024.bionlp-1.14"},{"key":"1399_CR95","doi-asserted-by":"crossref","unstructured":"Xu, Y., He, S., Chen, J., ZengXiangrong, Z., Wang, B., Liu, G., Zhao, J., Liu, K.: Llasa: Large language and structured data assistant. In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 1935\u20131946 (2025)","DOI":"10.18653\/v1\/2025.naacl-long.97"},{"key":"1399_CR96","unstructured":"Li, L., Ye, C., Ye, W., Sun, Y., Jiang, Z., Wang, H., Tian, J., Zhang, Y., WANG, N., Fu, X., Chen, G., Zhao, J.: Table as a modality for large language models. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025). https:\/\/openreview.net\/forum?id=kurEZdWU9G"},{"key":"1399_CR97","unstructured":"Robinson, J., Ranjan, R., Hu, W., Huang, K., Han, J., Dobles, A., Fey, M., Lenssen, J.E., Yuan, Y., Zhang, Z., et al.: Relational deep learning: Graph representation learning on relational databases. In: NeurIPS 2024 Third Table Representation Learning Workshop (2024)"},{"key":"1399_CR98","unstructured":"Niu, C., Song, Y., Song, J., Zhao, S., Grover, A., Ermon, S.: Permutation invariant graph generation via score-based generative modeling. In: International Conference on Artificial Intelligence and Statistics, pp. 4474\u20134484 (2020)"},{"key":"1399_CR99","doi-asserted-by":"crossref","unstructured":"Huang, H., Sun, L., Du, B., Fu, Y., Lv, W.: Graphgdp: Generative diffusion processes for permutation invariant graph generation. In: 2022 IEEE International Conference on Data Mining (ICDM), pp. 201\u2013210 (2022)","DOI":"10.1109\/ICDM54844.2022.00030"},{"key":"1399_CR100","first-page":"9559","volume":"34","author":"R Winter","year":"2021","unstructured":"Winter, R., No\u00e9, F., Clevert, D.-A.: Permutation-invariant variational autoencoder for graph-level representation learning. Adv. Neural. Inf. Process. Syst. 34, 9559\u20139573 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1399_CR101","doi-asserted-by":"crossref","unstructured":"Herzig, J., Nowak, P.K., Mueller, T., Piccinno, F., Eisenschlos, J.: Tapas: Weakly supervised table parsing via pre-training. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4320\u20134333 (2020)","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"1399_CR102","doi-asserted-by":"crossref","unstructured":"Yin, P., Neubig, G., Yih, W.-t., Riedel, S.: Tabert: Pretraining for joint understanding of textual and tabular data. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8413\u20138426 (2020)","DOI":"10.18653\/v1\/2020.acl-main.745"},{"issue":"1","key":"1399_CR103","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1145\/3542700.3542709","volume":"51","author":"X Deng","year":"2022","unstructured":"Deng, X., Sun, H., Lees, A., Wu, Y., Yu, C.: Turl: Table understanding through representation learning. ACM SIGMOD Rec. 51(1), 33\u201340 (2022)","journal-title":"ACM SIGMOD Rec."},{"key":"1399_CR104","doi-asserted-by":"crossref","unstructured":"Wang, Z., Dong, H., Jia, R., Li, J., Fu, Z., Han, S., Zhang, D.: Tuta: Tree-based transformers for generally structured table pre-training. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1780\u20131790 (2021)","DOI":"10.1145\/3447548.3467434"},{"key":"1399_CR105","first-page":"2902","volume":"35","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Sun, J.: Transtab: Learning transferable tabular transformers across tables. Adv. Neural. Inf. Process. Syst. 35, 2902\u20132915 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1399_CR106","unstructured":"Ye, C., Lu, G., Wang, H., Li, L., Wu, S., Chen, G., Zhao, J.: Ct-bert: learning better tabular representations through cross-table pre-training. (2023). arXiv:2307.04308"},{"key":"1399_CR107","doi-asserted-by":"crossref","unstructured":"Ammar, W., Darwish, K., El\u00a0Kahki, A., Hafez, K.: Ice-tea: in-context expansion and translation of english abbreviations. In: Computational Linguistics and Intelligent Text Processing: 12th International Conference, CICLing 2011, Tokyo, Japan, February 20-26, 2011. Proceedings, Part II 12, pp. 41\u201354 (2011)","DOI":"10.1007\/978-3-642-19437-5_4"},{"key":"1399_CR108","doi-asserted-by":"crossref","unstructured":"Veyseh, A.P.B., Dernoncourt, F., Tran, Q.H., Nguyen, T.H.: What does this acronym mean? introducing a new dataset for acronym identification and disambiguation. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 3285\u20133301 (2020)","DOI":"10.18653\/v1\/2020.coling-main.292"},{"key":"1399_CR109","doi-asserted-by":"crossref","unstructured":"Hulsebos, M., Hu, K., Bakker, M., Zgraggen, E., Satyanarayan, A., Kraska, T., Demiralp, \u00c7., Hidalgo, C.: Sherlock: A deep learning approach to semantic data type detection. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1500\u20131508 (2019)","DOI":"10.1145\/3292500.3330993"},{"issue":"12","key":"1399_CR110","doi-asserted-by":"publisher","first-page":"1835","DOI":"10.14778\/3407790.3407793","volume":"13","author":"D Zhang","year":"2020","unstructured":"Zhang, D., Hulsebos, M., Suhara, Y., Demiralp, \u00c7., Li, J., Tan, W.-C.: Sato: contextual semantic type detection in tables. Proceed. VLDB Endowment 13(12), 1835\u20131848 (2020)","journal-title":"Proceed. VLDB Endowment"},{"key":"1399_CR111","doi-asserted-by":"crossref","unstructured":"Suhara, Y., Li, J., Li, Y., Zhang, D., Demiralp, \u00c7., Chen, C., Tan, W.-C.: Annotating columns with pre-trained language models. In: Proceedings of the 2022 International Conference on Management of Data, pp. 1493\u20131503 (2022)","DOI":"10.1145\/3514221.3517906"},{"key":"1399_CR112","doi-asserted-by":"crossref","unstructured":"Wang, D., Shiralkar, P., Lockard, C., Huang, B., Dong, X.L., Jiang, M.: Tcn: Table convolutional network for web table interpretation. In: Proceedings of the Web Conference 2021, pp. 4020\u20134032 (2021)","DOI":"10.1145\/3442381.3450090"},{"key":"1399_CR113","doi-asserted-by":"crossref","unstructured":"Iida, H., Thai, D., Manjunatha, V., Iyyer, M.: Tabbie: Pretrained representations of tabular data. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3446\u20133456 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.270"},{"key":"1399_CR114","doi-asserted-by":"crossref","unstructured":"Liu, J., Li, Y., Lin, M.: Review of intent detection methods in the human-machine dialogue system. In: Journal of Physics: Conference Series, vol. 1267, pp. 012059 (2019)","DOI":"10.1088\/1742-6596\/1267\/1\/012059"},{"key":"1399_CR115","unstructured":"Zhou, J., Lu, T., Mishra, S., Brahma, S., Basu, S., Luan, Y., Zhou, D., Hou, L.: Instruction-following evaluation for large language models. (2023). arXiv:2311.07911"},{"key":"1399_CR116","unstructured":"Wu, J.J.: Does asking clarifying questions increases confidence in generated code? on the communication skills of large language models. (2023). arXiv:2308.13507"},{"key":"1399_CR117","doi-asserted-by":"crossref","unstructured":"Yu, T., Zhang, R., Er, H.Y., Li, S., Xue, E., Pang, B., Lin, X.V., Tan, Y.C., Shi, T., Li, Z., et al.: Cosql: A conversational text-to-sql challenge towards cross-domain natural language interfaces to databases. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019)","DOI":"10.18653\/v1\/D19-1204"},{"key":"1399_CR118","unstructured":"Floratou, A., Psallidas, F., Zhao, F., Deep, S., Hagleither, G., Tan, W., Cahoon, J., Alotaibi, R., Henkel, J., Singla, A., et al.: Nl2sql is a solved problem... not! In: CIDR (2024)"},{"key":"1399_CR119","doi-asserted-by":"crossref","unstructured":"Papicchio, S., Papotti, P., Cagliero, L.: Evaluating ambiguous questions in semantic parsing. In: 2024 IEEE 40th International Conference on Data Engineering Workshops (ICDEW), pp. 338\u2013342 (2024). IEEE","DOI":"10.1109\/ICDEW61823.2024.00050"},{"key":"1399_CR120","unstructured":"Hu, Z., Wang, C., Shu, Y., Paik, H.-Y., Zhu, L.: Ambiguity resolution in text-to-structured data mapping. (2025). arXiv:2505.11679"},{"key":"1399_CR121","doi-asserted-by":"crossref","unstructured":"Bhaskar, A., Tomar, T., Sathe, A., Sarawagi, S.: Benchmarking and improving text-to-sql generation under ambiguity. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 7053\u20137074 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.436"},{"key":"1399_CR122","unstructured":"Huang, Z., Damalapati, P.K., Wu, E.: Data ambiguity strikes back: How documentation improves gpt\u2019s text-to-sql. In: NeurIPS 2023 Second Table Representation Learning Workshop (2023)"},{"key":"1399_CR123","unstructured":"Wen, W., Pan, S., et al.: Schema-r1: A reasoning training approach for schema linking in text-to-sql task. (2025). arXiv:2506.11986"},{"issue":"1","key":"1399_CR124","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1002\/net.3230220105","volume":"22","author":"FK Hwang","year":"1992","unstructured":"Hwang, F.K., Richards, D.S.: Steiner tree problems. Networks 22(1), 55\u201389 (1992)","journal-title":"Networks"},{"issue":"2","key":"1399_CR125","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40763-6","volume":"19","author":"W Lu","year":"2025","unstructured":"Lu, W., Zhang, J., Fan, J., Fu, Z., Chen, Y., Du, X.: Large language model for table processing: A survey. Front. Comput. Sci. 19(2), 192350 (2025)","journal-title":"Front. Comput. Sci."},{"key":"1399_CR126","doi-asserted-by":"crossref","unstructured":"Gemmell, C., Dalton, J.: Generate, transform, answer: Question specific tool synthesis for tabular data. (2023). arXiv:2303.10138","DOI":"10.18653\/v1\/2023.emnlp-main.1003"},{"key":"1399_CR127","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q.V., Zhou, D., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1399_CR128","unstructured":"Jaech, A., Kalai, A., Lerer, A., Richardson, A., El-Kishky, A., Low, A., Helyar, A., Madry, A., Beutel, A., Carney, A., et al.: Openai o1 system card. (2024). arXiv:2412.16720"},{"key":"1399_CR129","unstructured":"Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X., et al.: Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. (2025). arXiv:2501.12948"},{"key":"1399_CR130","unstructured":"Wu, Z., Yang, J., Liu, J., Wu, X., Pan, C., Zhang, J., Zhao, Y., Song, S., Li, Y., Li, Z.: Table-r1: Region-based reinforcement learning for table understanding. (2025). arXiv:2505.12415"},{"key":"1399_CR131","unstructured":"Lei, F., Meng, J., Huang, Y., Chen, T., Zhang, Y., He, S., Zhao, J., Liu, K.: Reasoning-table: Exploring reinforcement learning for table reasoning. (2025). arXiv:2506.01710"},{"key":"1399_CR132","unstructured":"Zhong, V., Xiong, C., Socher, R.: Seq2sql: Generating structured queries from natural language using reinforcement learning. CoRR (2017). arXiv:1709.00103"},{"key":"1399_CR133","unstructured":"Dong, X., Zhang, C., Ge, Y., Mao, Y., Gao, Y., Lin, J., Lou, D., et al.: C3: Zero-shot text-to-sql with chatgpt. (2023). arXiv:2307.07306"},{"key":"1399_CR134","doi-asserted-by":"crossref","unstructured":"Nan, L., Zhao, Y., Zou, W., Ri, N., Tae, J., Zhang, E., Cohan, A., Radev, D.: Enhancing text-to-sql capabilities of large language models: A study on prompt design strategies. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 14935\u201314956 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.996"},{"key":"1399_CR135","doi-asserted-by":"publisher","unstructured":"Li, C., Shao, Y., Li, Y., Liu, Z.: Sea-sql: Semantic-enhanced text-to-sql with adaptive refinement. Frontiers of Computer Science, 0. https:\/\/doi.org\/10.1007\/s11704-025-41136-3","DOI":"10.1007\/s11704-025-41136-3"},{"key":"1399_CR136","doi-asserted-by":"crossref","unstructured":"Tai, C.-Y., Chen, Z., ZHANG, T., Deng, X., Sun, H.: Exploring chain of thought style prompting for text-to-sql. In: The 2023 Conference on Empirical Methods in Natural Language Processing (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.327"},{"key":"1399_CR137","doi-asserted-by":"crossref","unstructured":"Xie, T., Wu, C.H., Shi, P., Zhong, R., Scholak, T., Yasunaga, M., Wu, C.S., Zhong, M., Yin, P., Wang, S.I., et al.: Unifiedskg: Unifying and multi-tasking structured knowledge grounding with text-to-text language models. In: 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.39"},{"key":"1399_CR138","unstructured":"Gu, Z., Fan, J., Tang, N., Zhang, S., Zhang, Y., Chen, Z., Cao, L., Li, G., Madden, S., Du, X.: Interleaving pre-trained language models and large language models for zero-shot nl2sql generation. (2023). arXiv:2306.08891"},{"issue":"2","key":"1399_CR139","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3589292","volume":"1","author":"Z Gu","year":"2023","unstructured":"Gu, Z., Fan, J., Tang, N., Cao, L., Jia, B., Madden, S., Du, X.: Few-shot text-to-sql translation using structure and content prompt learning. Proceed. ACM Manag. Data 1(2), 1\u201328 (2023)","journal-title":"Proceed. ACM Manag. Data"},{"key":"1399_CR140","unstructured":"Zhang, Q., Dong, J., Chen, H., Li, W., Huang, F., Huang, X.: Structure guided large language model for sql generation. (2024). arXiv:2402.13284"},{"key":"1399_CR141","unstructured":"Li, Z., Wang, X., Zhao, J., Yang, S., Du, G., Hu, X., Zhang, B., Ye, Y., Li, Z., Zhao, R., et al.: Pet-sql: A prompt-enhanced two-stage text-to-sql framework with cross-consistency. (2024). arXiv:2403.09732"},{"key":"1399_CR142","unstructured":"Sui, G., Li, Z., Li, Z., Yang, S., Ruan, J., Mao, H., Zhao, R.: Reboost large language model-based text-to-sql, text-to-python, and text-to-function\u2013with real applications in traffic domain. (2023). arXiv:2310.18752"},{"key":"1399_CR143","doi-asserted-by":"crossref","unstructured":"Cen, J., Liu, J., Li, Z., Wang, J.: Sqlfixagent: Towards semantic-accurate text-to-sql parsing via consistency-enhanced multi-agent collaboration. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 49\u201357 (2025)","DOI":"10.1609\/aaai.v39i1.31979"},{"key":"1399_CR144","unstructured":"Lyu, S., Luo, H., Ou, Z., Zhu, Y., Shang, X., Qin, Y., Song, M.: Sql-o1: A self-reward heuristic dynamic search method for text-to-sql. (2025). arXiv:2502.11741"},{"issue":"3","key":"1399_CR145","doi-asserted-by":"publisher","first-page":"2497","DOI":"10.1007\/s10462-022-10228-y","volume":"56","author":"M \u015awiechowski","year":"2023","unstructured":"\u015awiechowski, M., Godlewski, K., Sawicki, B., Ma\u0144dziuk, J.: Monte carlo tree search: A review of recent modifications and applications. Artif. Intell. Rev. 56(3), 2497\u20132562 (2023)","journal-title":"Artif. Intell. Rev."},{"key":"1399_CR146","unstructured":"Pourreza, M., Talaei, S., Sun, R., Wan, X., Li, H., Mirhoseini, A., Saberi, A., Arik, S., et al.: Reasoning-sql: Reinforcement learning with sql tailored partial rewards for reasoning-enhanced text-to-sql. (2025). arXiv:2503.23157"},{"key":"1399_CR147","unstructured":"Ma, P., Zhuang, X., Xu, C., Jiang, X., Chen, R., Guo, J.: Sql-r1: Training natural language to sql reasoning model by reinforcement learning. (2025). arXiv:2504.08600"},{"key":"1399_CR148","doi-asserted-by":"crossref","unstructured":"Min, Q., Shi, Y., Zhang, Y.: A pilot study for chinese sql semantic parsing. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3652\u20133658 (2019)","DOI":"10.18653\/v1\/D19-1377"},{"issue":"10","key":"1399_CR149","first-page":"2996","volume":"42","author":"J Lyu","year":"2022","unstructured":"Lyu, J., Wang, X., Chen, G., Zhang, H., Wang, M.: Chinese text-to-sql model for industrial production. J. Comput. Applications 42(10), 2996 (2022)","journal-title":"J. Comput. Applications"},{"key":"1399_CR150","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H.P.d.O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al.: Evaluating large language models trained on code. (2021). arXiv:2107.03374"},{"key":"1399_CR151","unstructured":"Austin, J., Odena, A., Nye, M., Bosma, M., Michalewski, H., Dohan, D., Jiang, E., Cai, C., Terry, M., Le, Q., et al.: Program synthesis with large language models. (2021). arXiv:2108.07732"},{"key":"1399_CR152","unstructured":"Lai, Y., Li, C., Wang, Y., Zhang, T., Zhong, R., Zettlemoyer, L., Yih, W.-t., Fried, D., Wang, S., Yu, T.: Ds-1000: A natural and reliable benchmark for data science code generation. In: International Conference on Machine Learning, pp. 18319\u201318345 (2023)"},{"key":"1399_CR153","doi-asserted-by":"crossref","unstructured":"Barke, S., P\u00f6litz, C., Negreanu, C., Zorn, B., Cambronero, J., Gordon, A.D., Le, V., Nouri, E., Polikarpova, N., Sarkar, A., et al.: Solving data-centric tasks using large language models. In: NAACL-HLT (Findings) (2024)","DOI":"10.18653\/v1\/2024.findings-naacl.41"},{"issue":"8","key":"1399_CR154","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-025-4388-5","volume":"68","author":"X He","year":"2025","unstructured":"He, X., Xu, G., Han, X., Wang, Q., Zhao, L., Shen, C., Lin, C., Zhao, Z., Li, Q., Yang, L., et al.: Artificial intelligence security and privacy: a survey. Sci. China Inf. Sci. 68(8), 1\u201390 (2025)","journal-title":"Sci. China Inf. Sci."},{"key":"1399_CR155","doi-asserted-by":"crossref","unstructured":"Lin, M., Zhang, H., Lao, J., Li, R., Zhou, Y., Yang, C., Cao, Y., Tang, M.: Are your llm-based text-to-sql models secure? exploring sql injection via backdoor attacks. (2025). arXiv:2503.05445","DOI":"10.1145\/3769762"},{"key":"1399_CR156","doi-asserted-by":"crossref","unstructured":"Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., Zhang, Y.: A survey on large language model (llm) security and privacy: The good, the bad, and the ugly. High-Confidence Computing, 100211 (2024)","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"1399_CR157","unstructured":"Kumar, A., Agarwal, C., Srinivas, S., Li, A.J., Feizi, S., Lakkaraju, H.: Certifying llm safety against adversarial prompting. In: First Conference on Language Modeling (2024)"},{"key":"1399_CR158","first-page":"1502","volume":"37","author":"S Xhonneux","year":"2024","unstructured":"Xhonneux, S., Sordoni, A., G\u00fcnnemann, S., Gidel, G., Schwinn, L.: Efficient adversarial training in llms with continuous attacks. Adv. Neural. Inf. Process. Syst. 37, 1502\u20131530 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"1399_CR159","first-page":"323","volume":"35","author":"S Kim","year":"2025","unstructured":"Kim, S., Lee, S.: Research on sql injection fuzzing using llm. J. Korea Institute Inf. Sec. Cryptol. 35(2), 323\u2013334 (2025)","journal-title":"J. Korea Institute Inf. Sec. Cryptol."},{"key":"1399_CR160","doi-asserted-by":"crossref","unstructured":"Margeloiu, A., Simidjievski, N., Lio, P., Jamnik, M.: Weight predictor network with feature selection for small sample tabular biomedical data. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 9081\u20139089 (2023)","DOI":"10.1609\/aaai.v37i8.26090"},{"key":"1399_CR161","unstructured":"Zhao, Y., Liu, H., Long, Y., Zhang, R., Zhao, C., Cohan, A.: Knowledgemath: Knowledge-intensive math word problem solving in finance domains. (2023). arXiv:2311.09797"},{"key":"1399_CR162","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., Cao, Y.: React: Synergizing reasoning and acting in language models. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"1399_CR163","doi-asserted-by":"crossref","unstructured":"Li, J., Wu, T., Mao, Y., Gao, Y., Feng, Y., Liu, H.: Sql-factory: A multi-agent framework for high-quality and large-scale sql generation. (2025). arXiv:2504.14837","DOI":"10.14778\/3778092.3778093"},{"key":"1399_CR164","unstructured":"Hui, B., Yang, J., Cui, Z., Yang, J., Liu, D., Zhang, L., Liu, T., Zhang, J., Yu, B., Dang, K., et al.: Qwen2. 5-coder technical report. (2024). arXiv:2409.12186"},{"key":"1399_CR165","unstructured":"Team, Q.: QwQ-32B: Embracing the Power of Reinforcement Learning (2025). https:\/\/qwenlm.github.io\/blog\/qwq-32b\/"},{"key":"1399_CR166","unstructured":"Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., Zhao, C., Deng, C., Zhang, C., Ruan, C., et al.: Deepseek-v3 technical report. (2024). arXiv:2412.19437"},{"key":"1399_CR167","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighoff, N., Lian, D., Nie, J.-Y.: C-pack: Packed resources for general chinese embeddings. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 641\u2013649 (2024)","DOI":"10.1145\/3626772.3657878"},{"key":"1399_CR168","doi-asserted-by":"publisher","first-page":"126118","DOI":"10.52202\/079017-4007","volume":"37","author":"J Guan","year":"2024","unstructured":"Guan, J., Wu, W., Xu, P., Wang, H., Huang, M., et al.: Amor: A recipe for building adaptable modular knowledge agents through process feedback. Adv. Neural. Inf. Process. Syst. 37, 126118\u2013126148 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1399_CR169","doi-asserted-by":"crossref","unstructured":"Yue, Y., Zhang, G., Liu, B., Wan, G., Wang, K., Cheng, D., Qi, Y.: Masrouter: Learning to route llms for multi-agent systems. (2025). arXiv:2502.11133","DOI":"10.18653\/v1\/2025.acl-long.757"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-025-01399-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11280-025-01399-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-025-01399-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T14:36:06Z","timestamp":1774881366000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11280-025-01399-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,20]]},"references-count":169,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["1399"],"URL":"https:\/\/doi.org\/10.1007\/s11280-025-01399-z","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"value":"1386-145X","type":"print"},{"value":"1573-1413","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,20]]},"assertion":[{"value":"17 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2026","order":4,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"16"}}