{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:15:27Z","timestamp":1772910927670,"version":"3.50.1"},"reference-count":50,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2023YFB4503600, 2022ZD0119100"],"award-info":[{"award-number":["2023YFB4503600, 2022ZD0119100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSF of China","doi-asserted-by":"crossref","award":["62525202, 62232009, 62025204, 62432007, 62502304"],"award-info":[{"award-number":["62525202, 62232009, 62025204, 62432007, 62502304"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shenzhen Project","award":["CJGJZD20230724093403007"],"award-info":[{"award-number":["CJGJZD20230724093403007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2025,12,4]]},"abstract":"<jats:p>Semi-structured tables, widely used in real-world applications (e.g., financial reports, medical records, transactional orders), often involve flexible and complex layouts (e.g., hierarchical headers and merged cells). These tables generally rely on human analysts to interpret table layouts and answer relevant natural language questions, which is costly and inefficient. To automate the procedure, existing methods face significant challenges. First, methods like NL2SQL require converting semi-structured tables into structured ones, which often causes substantial information loss. Second, methods like NL2Code and multi-modal LLM QA struggle to understand the complex layouts of semi-structured tables and cannot accurately answer corresponding questions.<\/jats:p>\n                  <jats:p>\n                    To this end, we propose ST-Raptor, a tree-based framework for semi-structured table question answering (\n                    <jats:italic toggle=\"yes\">semi-structured table QA<\/jats:italic>\n                    ) using large language models. First, we introduce the Hierarchical Orthogonal Tree (HO-Tree), a structural model that captures complex semi-structured table layouts, along with an effective algorithm for constructing the tree by identifying headers, content values, and their implicit relationships. Second, we define a set of basic tree operations to guide LLMs in executing common QA tasks. Given a user question, ST-Raptor decomposes it into simpler sub-questions, generates corresponding tree operation pipelines, and conducts operation-table alignment for accurate pipeline execution. Third, we incorporate a two-stage verification mechanism: (1) forward validation checks the correctness of execution steps, while (2) backward validation evaluates answer reliability by reconstructing queries from predicted answers. To benchmark the performance, we present SSTQA, a dataset of 764 questions over 102 real-world semi-structured tables. Experiments show that ST-Raptor outperforms nine baselines by up to 20% in answer accuracy. The code is available at https:\/\/github.com\/weAIDB\/ST-Raptor.\n                  <\/jats:p>","DOI":"10.1145\/3769829","type":"journal-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:32:13Z","timestamp":1764995533000},"page":"1-27","source":"Crossref","is-referenced-by-count":2,"title":["ST-Raptor: LLM-Powered Semi-Structured Table Question Answering"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3449-4248","authenticated-orcid":false,"given":"Zirui","family":"Tang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2343-643X","authenticated-orcid":false,"given":"Boyu","family":"Niu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2285-7836","authenticated-orcid":false,"given":"Xuanhe","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6313-2138","authenticated-orcid":false,"given":"Boxiu","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8862-7753","authenticated-orcid":false,"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8229-3622","authenticated-orcid":false,"given":"Jiannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Vancouver, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1398-0621","authenticated-orcid":false,"given":"Guoliang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1653-2485","authenticated-orcid":false,"given":"Xinyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0965-9058","authenticated-orcid":false,"given":"Fan","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,5]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"[n.d.]. https:\/\/www.frontiersin.org\/research-topics\/21489\/knowledge-discovery-from-unstructured-data-in-finance"},{"key":"e_1_2_1_2_1","unstructured":"[n.d.]. https:\/\/enterprises.upmc.com\/resources\/insights\/health-cares-unstructured-data-challenge\/"},{"key":"e_1_2_1_3_1","unstructured":"[n.d.]. https:\/\/pages.cs.wisc.edu\/~jbeckham\/TR\/cnet.pdf"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-62222-5_33"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2024.1211004"},{"key":"e_1_2_1_6_1","unstructured":"Simran Arora Brandon Yang Sabri Eyuboglu Avanika Narayan Andrew Hojel Immanuel Trummer and Christopher R\u00e9. 2025. Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes. arXiv:2304.09433 [cs.CL] https:\/\/arxiv.org\/abs\/2304.09433"},{"key":"e_1_2_1_7_1","unstructured":"Camille Barboule Benjamin Piwowarski and Yoan Chabot. 2025. Survey on Question Answering over Visually Rich Documents: Methods Challenges and Trends. arXiv:2501.02235 [cs.CL] https:\/\/arxiv.org\/abs\/2501.02235"},{"key":"e_1_2_1_8_1","unstructured":"Lukasz Borchmann and Marek Wydmuch. 2025. Query and Conquer: Execution-Guided SQL Generation. arXiv:2503.24364 [cs.CL] https:\/\/arxiv.org\/abs\/2503.24364"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415563"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3709719"},{"key":"e_1_2_1_11_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu Lixin Gu Xuehui Wang Qingyun Li Yimin Ren Zixuan Chen Jiapeng Luo Jiahao Wang Tan Jiang Bo Wang Conghui He Botian Shi Xingcheng Zhang Han Lv Yi Wang Wenqi Shao Pei Chu Zhongying Tu Tong He Zhiyong Wu Huipeng Deng Jiaye Ge Kai Chen Kaipeng Zhang Limin Wang Min Dou Lewei Lu Xizhou Zhu Tong Lu Dahua Lin Yu Qiao Jifeng Dai and Wenhai Wang. 2025. Expanding Performance Boundaries of Open-Source Multimodal Models with Model Data and Test-Time Scaling. arXiv:2412.05271 [cs.CV] https:\/\/arxiv.org\/abs\/2412.05271"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/362384.362685"},{"key":"e_1_2_1_13_1","unstructured":"DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 [cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_2_1_14_1","unstructured":"DeepSeek-AI Aixin Liu Bei Feng et al. 2025. DeepSeek-V3 Technical Report. arXiv:2412.19437 [cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.23"},{"key":"e_1_2_1_16_1","unstructured":"Yingqi Gao Yifu Liu Xiaoxia Li Xiaorong Shi Yin Zhu Yiming Wang Shiqi Li Wei Li Yuntao Hong Zhiling Luo Jinyang Gao Liyu Mou and Yu Li. 2025. A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL. arXiv:2411.08599 [cs.AI] https:\/\/arxiv.org\/abs\/2411.08599"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.149"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.149"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"e_1_2_1_20_1","unstructured":"Anwen Hu Haiyang Xu Jiabo Ye Ming Yan Liang Zhang Bo Zhang Chen Li Ji Zhang Qin Jin Fei Huang and Jingren Zhou. 2024. mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding. arXiv:2403.12895 [cs.CV] https:\/\/arxiv.org\/abs\/2403.12895"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1045"},{"key":"e_1_2_1_22_1","volume-title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks. arXiv:2210.02406 [cs.CL] https:\/\/arxiv.org\/abs\/2210.02406","author":"Khot Tushar","year":"2023","unstructured":"Tushar Khot, Harsh Trivedi, Matthew Finlayson, Yao Fu, Kyle Richardson, Peter Clark, and Ashish Sabharwal. 2023. Decomposed Prompting: A Modular Approach for Solving Complex Tasks. arXiv:2210.02406 [cs.CL] https:\/\/arxiv.org\/abs\/2210.02406"},{"key":"e_1_2_1_23_1","volume-title":"Dongmei Zhang, and Surajit Chaudhuri.","author":"Li Peng","year":"2023","unstructured":"Peng Li, Yeye He, Dror Yashar, Weiwei Cui, Song Ge, Haidong Zhang, Danielle Rifinski Fainman, Dongmei Zhang, and Surajit Chaudhuri. 2023. Table-GPT: Table-tuned GPT for Diverse Table Tasks. arXiv:2310.09263 [cs.CL] https:\/\/arxiv.org\/abs\/2310.09263"},{"key":"e_1_2_1_24_1","unstructured":"Zhishuai Li Xiang Wang Jingjing Zhao Sun Yang Guoqing Du Xiaoru Hu Bin Zhang Yuxiao Ye Ziyue Li Rui Zhao and Hangyu Mao. 2024. PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency. arXiv:2403.09732 [cs.CL] https:\/\/arxiv.org\/abs\/2403.09732"},{"key":"e_1_2_1_25_1","volume-title":"Parameswaran","author":"Lin Yiming","year":"2025","unstructured":"Yiming Lin, Mawil Hasan, Rohan Kosalge, Alvin Cheung, and Aditya G. Parameswaran. 2025. TWIX: Automatically Reconstructing Structured Data from Templatized Documents. arXiv:2501.06659 [cs.DB] https:\/\/arxiv.org\/abs\/2501.06659"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28149"},{"key":"e_1_2_1_27_1","unstructured":"Nelson F. Liu Kevin Lin John Hewitt Ashwin Paranjape Michele Bevilacqua Fabio Petroni and Percy Liang. 2023. Lost in the Middle: How Language Models Use Long Contexts. arXiv:2307.03172 [cs.CL] https:\/\/arxiv.org\/abs\/2307.03172"},{"key":"e_1_2_1_28_1","unstructured":"Jinwei Lu Yuanfeng Song Zhiqian Qin Haodi Zhang Chen Zhang and Raymond Chi-Wing Wong. 2025. Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation. arXiv:2502.11201 [cs.DB] https:\/\/arxiv.org\/abs\/2502.11201"},{"key":"e_1_2_1_29_1","unstructured":"OpenAI. 2024. GPT-4o System Card. arXiv:2410.21276 [cs.CL] https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_2_1_30_1","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"e_1_2_1_33_1","volume-title":"A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions. arXiv preprint arXiv:2208.13629","author":"Qin Bowen","year":"2022","unstructured":"Bowen Qin, Binyuan Hui, Lihan Wang, Min Yang, Jinyang Li, Binhua Li, Ruiying Geng, Rongyu Cao, Jian Sun, Luo Si, Fei Huang, and Yongbin Li. 2022. A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions. arXiv preprint arXiv:2208.13629 (2022). https:\/\/arxiv.org\/abs\/2208.13629"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.324"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.779"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.74"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635752"},{"key":"e_1_2_1_38_1","unstructured":"Zirui Tang Weizheng Wang Zihang Zhou Yang Jiao Bangrui Xu Boyu Niu Xuanhe Zhou Guoliang Li Yeye He Wei Zhou et al. 2025. LLM\/Agent-as-Data-Analyst: A Survey. arXiv preprint arXiv:2509.23988 (2025)."},{"key":"e_1_2_1_39_1","first-page":"1941","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics, Emily M. Bender, Leon Derczynski, and Pierre Isabelle (Eds.). Association for Computational Linguistics","author":"Wang Hao","year":"2018","unstructured":"Hao Wang, Xiaodong Zhang, Shuming Ma, Xu Sun, Houfeng Wang, and Mengxiang Wang. 2018. A Neural Question Answering Model Based on Semi-Structured Tables. In Proceedings of the 27th International Conference on Computational Linguistics, Emily M. Bender, Leon Derczynski, and Pierre Isabelle (Eds.). Association for Computational Linguistics, Santa Fe, New Mexico, USA, 1941-1951. https:\/\/aclanthology.org\/C18-1165\/"},{"key":"e_1_2_1_40_1","unstructured":"Liang Wang Nan Yang Xiaolong Huang Linjun Yang Rangan Majumder and Furu Wei. 2024. Multilingual E5 Text Embeddings: A Technical Report. arXiv:2402.05672 [cs.CL] https:\/\/arxiv.org\/abs\/2402.05672"},{"key":"e_1_2_1_41_1","unstructured":"Zhongyuan Wang Richong Zhang Zhijie Nie and Jaein Kim. 2024. Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios. arXiv:2408.16991 [cs.CL] https:\/\/arxiv.org\/abs\/2408.16991"},{"key":"e_1_2_1_42_1","unstructured":"Xiangjin Xie Guangwei Xu Lingyan Zhao and Ruijie Guo. 2025. OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment. arXiv:2502.14913 [cs.CL] https:\/\/arxiv.org\/abs\/2502.14913"},{"key":"e_1_2_1_43_1","unstructured":"Yunhu Ye Binyuan Hui Min Yang Binhua Li Fei Huang and Yongbin Li. 2023. Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning. arXiv:2301.13808 [cs.CL] https:\/\/arxiv.org\/abs\/2301.13808"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.411"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.335"},{"key":"e_1_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Xiaokang Zhang Sijia Luo Bohan Zhang Zeyao Ma Jing Zhang Yang Li Guanlin Li Zijun Yao Kangli Xu Jinchang Zhou Daniel Zhang-Li Jifan Yu Shu Zhao Juanzi Li and Jie Tang. 2025. TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios. arXiv:2403.19318 [cs.CL] https:\/\/arxiv.org\/abs\/2403.19318","DOI":"10.18653\/v1\/2025.findings-acl.538"},{"key":"e_1_2_1_47_1","volume-title":"Patel","author":"Zhang Yunjia","year":"2023","unstructured":"Yunjia Zhang, Jordan Henkel, Avrilia Floratou, Joyce Cahoon, Shaleen Deep, and Jignesh M. Patel. 2023. ReAcTable: Enhancing ReAct for Table Question Answering. arXiv:2310.00815 [cs.DB] https:\/\/arxiv.org\/abs\/2310.00815"},{"key":"e_1_2_1_48_1","unstructured":"Mingyu Zheng Xinwei Feng Qingyi Si Qiaoqiao She Zheng Lin Wenbin Jiang and Weiping Wang. 2024. Multimodal Table Understanding. arXiv:2406.08100 [cs.CL] https:\/\/arxiv.org\/abs\/2406.08100"},{"key":"e_1_2_1_49_1","unstructured":"Xuanhe Zhou Junxuan He Wei Zhou Haodong Chen Zirui Tang Haoyu Zhao Xin Tong Guoliang Li Youmin Chen Jun Zhou et al. 2025. A Survey of LLM\u00d7 DATA. arXiv preprint arXiv:2505.18458 (2025)."},{"key":"e_1_2_1_50_1","unstructured":"Fengbin Zhu Ziyang Liu Fuli Feng ChaoWang Moxin Li and Tat-Seng Chua. 2024. TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data. arXiv:2401.13223 [cs.CL] https:\/\/arxiv.org\/abs\/2401.13223"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3769829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T23:29:32Z","timestamp":1768087772000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769829"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":50,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12,4]]}},"alternative-id":["10.1145\/3769829"],"URL":"https:\/\/doi.org\/10.1145\/3769829","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]}}}