{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:13Z","timestamp":1786120813979,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Natural Science Foundation of China","award":["62432011"],"award-info":[{"award-number":["62432011"]}]},{"name":"Fujian Provincial Natural Science Foundation of China","award":["2025J010001"],"award-info":[{"award-number":["2025J010001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817487","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"9302-9313","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automating End-to-End Hybrid Query Processing: Benchmark, Solution, and Insights"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2279-1491","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"first","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0120-1698","authenticated-orcid":false,"given":"Chenzhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7605-3815","authenticated-orcid":false,"given":"Longkang","family":"Lin","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1398-0621","authenticated-orcid":false,"given":"Guoliang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2275-997X","authenticated-orcid":false,"given":"Chen","family":"Lin","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Asim Biswal Liana Patel Siddarth Jha Amog Kamsetty Shu Liu Joseph E. Gonzalez Carlos Guestrin and Matei Zaharia. 2025. Text2SQL Is Not Enough: Unifying AI and Databases with TAG. In CIDR. www.cidrdb.org."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Saumya Chaturvedi Aman Chadha and Laurent Bindschaedler. 2025. SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction. arXiv:2509.00581 [cs] doi:10.48550\/arXiv.2509.00581","DOI":"10.48550\/arXiv.2509.00581"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 38th International Conference, on Neural Information Processing Systems (NIPS, '24","volume":"74921","author":"Chen Si-An","year":"2025","unstructured":"Si-An Chen, Lesly Miculicich, Julian Martin Eisenschlos, Zifeng Wang, Zilong Wang, Yanfei Chen, Yasuhisa Fujii, Hsuan-Tien Lin, Chen-Yu Lee, and Tomas Pfister. 2025. TableRAG: Million-Token Table Understanding with Language Models. In Proceedings of the 38th International Conference, on Neural Information Processing Systems (NIPS, '24, Vol. V37). Curran Associates Inc., Red Hook, NY, USA, 74899-74921."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of ICLR 2021","author":"Chen Wenhu","year":"2021","unstructured":"Wenhu Chen, Ming-Wei Chang, Eva Schlinger, William Wang, and William W Cohen. 2021. Open Question Answering over Tables and Text. Proceedings of ICLR 2021 (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.91"},{"key":"e_1_3_2_1_6_1","volume-title":"Vabs\/2210.02875","author":"Cheng Zhoujun","year":"2023","unstructured":"Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Caiming Xiong, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, and Tao Yu. 2023. Binding Language Models in Symbolic Languages. ICLR, Vabs\/2210.02875 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.00075"},{"key":"e_1_3_2_1_8_1","unstructured":"DeepSeek-AI. 2024. DeepSeek-V3 Technical Report. arXiv:2412.19437 [cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Google Gemini Team. 2025. Gemini 2.5: Pushing the Frontier with Advanced Reasoning Multimodality Long Context and Next Generation Agentic Capabilities. arXiv:2507.06261 [cs] doi:10.48550\/arXiv.2507.06261","DOI":"10.48550\/arXiv.2507.06261"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.25"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Zijin Hong Zheng Yuan Qinggang Zhang Hao Chen Junnan Dong Feiran Huang and Xiao Huang. 2025. Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL. arXiv:2406.08426 [cs] doi:10.48550\/arXiv.2406.08426","DOI":"10.48550\/arXiv.2406.08426"},{"key":"e_1_3_2_1_13_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1167"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Nengzheng Jin Joanna Siebert Dongfang Li and Qingcai Chen. 2022. A Survey on Table Question Answering: Recent Advances. arXiv:2207.05270 [cs] doi:10.48550\/arXiv.2207.05270","DOI":"10.48550\/arXiv.2207.05270"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.14445\/23488387\/IJCSE-V10I5P103"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2601.16432"},{"key":"e_1_3_2_1_18_1","volume-title":"The Thirteenth International Conference, on Learning Representations.","author":"Lei Fangyu","year":"2024","unstructured":"Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, and Tao Yu. 2024. Spider 2.0: Evaluating Language Models, on Real-World Enterprise Text-to-SQL Workflows. In The Thirteenth International Conference, on Learning Representations."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3682003"},{"key":"e_1_3_2_1_20_1","unstructured":"Jinyang Li Binyuan Hui Ge Qu Jiaxi Yang Binhua Li Bowen Li Bailin Wang Bowen Qin Ruiying Geng Nan Huo et al. 2024b. 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 V36 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654979"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.551"},{"key":"e_1_3_2_1_23_1","volume-title":"A Survey of NL2SQL with Large Language Models: Where are we, and where are we going? arXiv preprint arXiv:2408.05109","author":"Liu Xinyu","year":"2024","unstructured":"Xinyu Liu, Shuyu Shen, Boyan Li, Peixian Ma, Runzhi Jiang, Yuxin Zhang, Ju Fan, Guoliang Li, Nan Tang, and Yuyu Luo. 2024. A Survey of NL2SQL with Large Language Models: Where are we, and where are we going? arXiv preprint arXiv:2408.05109 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.221"},{"key":"e_1_3_2_1_25_1","volume-title":"News Category Dataset. arXiv preprint arXiv:2209.11429","author":"Misra Rishabh","year":"2022","unstructured":"Rishabh Misra. 2022. News Category Dataset. arXiv preprint arXiv:2209.11429 (2022)."},{"key":"e_1_3_2_1_26_1","unstructured":"Rishabh Misra and Jigyasa Grover. 2021. Sculpting Data for ML: The first act of Machine Learning."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"e_1_3_2_1_28_1","unstructured":"OpenAI. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs] doi:10.48550\/arXiv.2303.08774"},{"key":"e_1_3_2_1_29_1","unstructured":"OpenAI. 2025. GPT-5.1: A smarter more conversational ChatGPT. https:\/\/openai.com\/index\/gpt-5-1"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3749646.3749685"},{"key":"e_1_3_2_1_32_1","volume-title":"Text-to-SQL. In The Thirteenth International Conference, on Learning Representations.","author":"Pourreza Mohammadreza","unstructured":"Mohammadreza Pourreza, Hailong Li, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, and Sercan O. Arik. 2024. CHASE-SQL: Multi-Path Reasoning, and Preference Optimized Candidate Selection, in Text-to-SQL. In The Thirteenth International Conference, on Learning Representations."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1577"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.481"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3320212"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 31st International Conference, on Computational Linguistics, Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa","author":"Shi Jie","unstructured":"Jie Shi, Bo Xu, Jiaqing Liang, Yanghua Xiao, Jia Chen, Chenhao Xie, Peng Wang, and Wei Wang. 2025. Gen-SQL: Efficient Text-to-SQL By Bridging Natural Language Question And Database Schema With Pseudo-Schema. In Proceedings of the 31st International Conference, on Computational Linguistics, Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, and Steven Schockaert (Eds.). Association for Computational Linguistics, Abu Dhabi, UAE, 3794-3807."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Vladislav Shkapenyuk Divesh Srivastava Theodore Johnson and Parisa Ghane. 2025. Automatic Metadata Extraction for Text-to-SQL. arXiv:2505.19988 [cs] doi:10.48550\/arXiv.2505.19988","DOI":"10.48550\/arXiv.2505.19988"},{"key":"e_1_3_2_1_38_1","unstructured":"Qwen Team. 2025a. Qwen2.5 Technical Report. arXiv:2412.15115 [cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_1_39_1","unstructured":"Qwen Team. 2025b. Qwen3 Technical Report. arXiv:2505.09388 [cs.CL] https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","unstructured":"Pengfei Wang Baolin Sun Xuemei Dong Yaxun Dai Hongwei Yuan Mengdie Chu Yingqi Gao Xiang Qi Peng Zhang and Ying Yan. 2025. Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling. arXiv:2509.24403 [cs] doi:10.48550\/arXiv.2509.24403","DOI":"10.48550\/arXiv.2509.24403"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00309"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.331"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","unstructured":"Tao Yu Rui Zhang Kai Yang Michihiro Yasunaga Dongxu Wang Zifan Li James Ma Irene Li Qingning Yao Shanelle Roman Zilin Zhang and Dragomir Radev. 2018. 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 Ellen Riloff David Chiang Julia Hockenmaier and Jun'ichi Tsujii (Eds.). Association for Computational Linguistics Brussels Belgium 3911-3921. doi:10.18653\/v1\/D18-1425","DOI":"10.18653\/v1\/D18-1425"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34770"},{"key":"e_1_3_2_1_45_1","unstructured":"Fuheng Zhao Divyakant Agrawal and Amr El Abbadi. 2025. Hybrid Querying Over Relational Databases and Large Language Models. In CIDR. www.cidrdb.org."},{"key":"e_1_3_2_1_46_1","volume-title":"Vabs\/1709.00103","author":"Zhong Victor","year":"2017","unstructured":"Victor Zhong, Caiming Xiong, and Richard Socher. 2017. Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning. CoRR, Vabs\/1709.00103 (2017)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:32:14Z","timestamp":1786066334000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817487"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":46,"alternative-id":["10.1145\/3770855.3817487","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817487","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}