{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T11:20:48Z","timestamp":1784373648336,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T00:00:00Z","timestamp":1709510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"DOI":"10.1145\/3616855.3635752","type":"proceedings-article","created":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T18:18:12Z","timestamp":1709576292000},"page":"645-654","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":124,"title":["Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8559-831X","authenticated-orcid":false,"given":"Yuan","family":"Sui","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0322-7513","authenticated-orcid":false,"given":"Mengyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5781-4756","authenticated-orcid":false,"given":"Mingjie","family":"Zhou","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0360-6089","authenticated-orcid":false,"given":"Shi","family":"Han","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9230-2799","authenticated-orcid":false,"given":"Dongmei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Pranjal Aggarwal Aman Madaan Yiming Yang and Mausam. 2023. Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning with LLMs. https: \/\/doi.org\/10.48550\/arXiv.2305.11860 arXiv:2305.11860 [cs]","DOI":"10.48550\/arXiv.2305.11860"},{"key":"e_1_3_2_1_2_1","volume-title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models. arXiv:2107.06955 [cs] http:\/\/arxiv.org\/abs\/2107.06955","author":"Aghajanyan Armen","year":"2021","unstructured":"Armen Aghajanyan, Dmytro Okhonko, Mike Lewis, Mandar Joshi, Hu Xu, Gargi Ghosh, and Luke Zettlemoyer. 2021. HTLM: Hyper-Text Pre-Training and Prompting of Language Models. arXiv:2107.06955 [cs] http:\/\/arxiv.org\/abs\/2107.06955"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.05707"},{"key":"e_1_3_2_1_4_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Dhariwal, et al. 2020. Language Models Are Few-Shot Learners. In Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 1877--1901. https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/ 1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.03374"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Wenhu Chen. 2022. Large Language Models Are Few(1)-Shot Table Reasoners. https:\/\/doi.org\/10.48550\/arXiv.2210.06710 arXiv:2210.06710 [cs]","DOI":"10.48550\/arXiv.2210.06710"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Wenhu Chen Hongmin Wang Jianshu Chen Yunkai Zhang Hong Wang Shiyang Li Xiyou Zhou and William Yang Wang. 2020. TabFact: A Large-Scale Dataset for Table-Based Fact Verification. https:\/\/doi.org\/10.48550\/arXiv.1909.02164 arXiv:1909.02164 [cs]","DOI":"10.48550\/arXiv.1909.02164"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.91"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma Albert Webson Shixiang Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Alex Castro-Ros Marie Pellat Kevin Robinson Dasha Valter Sharan Narang Gaurav Mishra Adams Yu Vincent Zhao Yanping Huang Andrew Dai Hongkun Yu Slav Petrov Ed H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc V. Le and Jason Wei. 2022. Scaling Instruction-Finetuned Language Models. https:\/\/doi.org\/10.48550\/arXiv.2210.11416 arXiv:2210.11416 [cs]","DOI":"10.48550\/arXiv.2210.11416"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. https:\/\/doi.org\/10.48550\/arXiv.2110.14168 arXiv:2110.14168 [cs]","DOI":"10.48550\/arXiv.2110.14168"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.09745"},{"key":"e_1_3_2_1_13_1","unstructured":"Longxu Dou Yan Gao Mingyang Pan Dingzirui Wang Wanxiang Che Dechen Zhan and Jian-Guang Lou. 2022. UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL. arXiv:2203.07781 [cs] http: \/\/arxiv.org\/abs\/2203.07781"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.04312"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615187"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.179"},{"key":"e_1_3_2_1_17_1","unstructured":"Xinyi He Mengyu Zhou Jialiang Xu Xiao Lv Tianle Li Yijia Shao Shi Han Zejian Yuan and Dongmei Zhang. 2022. Inferring Tabular Analysis Metadata by Infusing Distribution and Knowledge Information. https:\/\/doi.org\/10.48550\/ arXiv.2209.00946 arXiv:2209.00946 [cs]"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Madelon Hulsebos and Paul Groth. 2022. GitTables: A LargeScale Corpus of Relational Tables. https:\/\/doi.org\/10.48550\/arXiv.2106.07258 arXiv:2106.07258 [cs]","DOI":"10.48550\/arXiv.2106.07258"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1167"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.11916"},{"key":"e_1_3_2_1_23_1","unstructured":"Stephanie Lin Jacob Hilton and Owain Evans. 2022. TruthfulQA: Measuring How Models Mimic Human Falsehoods. arXiv:2109.07958 [cs] http:\/\/arxiv.org\/ abs\/2109.07958"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.08387"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.07653"},{"key":"e_1_3_2_1_26_1","unstructured":"Ahmed Nassar Nikolaos Livathinos Maksym Lysak and Peter Staar. 2022. TableFormer: Table Structure Understanding with Transformers. https:\/\/doi.org\/10. 48550\/arXiv.2203.01017 arXiv:2203.01017 [cs]"},{"key":"e_1_3_2_1_27_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. https:\/\/doi.org\/10.48550\/arXiv.2303.08774 arXiv:2303.08774 [cs]"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul Christiano Jan Leike and Ryan Lowe. 2022. Training Language Models to Follow Instructions with Human Feedback. https: \/\/doi.org\/10.48550\/arXiv.2203.02155 arXiv:2203.02155 [cs]","DOI":"10.48550\/arXiv.2203.02155"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Ankur P. Parikh Xuezhi Wang Sebastian Gehrmann Manaal Faruqui Bhuwan Dhingra Diyi Yang and Dipanjan Das. 2020. ToTTo: A Controlled TableTo-Text Generation Dataset. https:\/\/doi.org\/10.48550\/arXiv.2004.14373 arXiv:2004.14373 [cs]","DOI":"10.48550\/arXiv.2004.14373"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Jack W. Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Song et al. 2022. Scaling Language Models: Methods Analysis & Insights from Training Gopher. https:\/\/doi.org\/10.48550\/arXiv.2112.11446 arXiv:2112.11446 [cs]","DOI":"10.48550\/arXiv.2112.11446"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","unstructured":"Yijia Shao Mengyu Zhou Yifan Zhong Tao Wu Hongwei Han Shi Han Gideon Huang and Dongmei Zhang. 2022. FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information. https: \/\/doi.org\/10.48550\/arXiv.2211.05284 arXiv:2211.05284 [cs]","DOI":"10.48550\/arXiv.2211.05284"},{"key":"e_1_3_2_1_32_1","unstructured":"Alon Talmor Ori Yoran Amnon Catav Dan Lahav Yizhong Wang Akari Asai Gabriel Ilharco Hannaneh Hajishirzi and Jonathan Berant. 2021. MultiModalQA: Complex Question Answering over Text Tables and Images. https:\/\/doi.org\/10. 48550\/arXiv.2104.06039 arXiv:2104.06039 [cs]"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.06732"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511972"},{"key":"e_1_3_2_1_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/ 3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467434"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.11903"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","unstructured":"Tianbao Xie Chen Henry Wu Peng Shi Ruiqi Zhong Torsten Scholak Michihiro Yasunaga Chien-Sheng Wu Ming Zhong Pengcheng Yin Sida I. Wang Victor Zhong Bailin Wang Chengzu Li Connor Boyle Ansong Ni Ziyu Yao Dragomir Radev Caiming Xiong Lingpeng Kong Rui Zhang Noah A. Smith Luke Zettlemoyer and Tao Yu. 2022. UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models. https: \/\/doi.org\/10.48550\/arXiv.2201.05966 arXiv:2201.05966 [cs]","DOI":"10.48550\/arXiv.2201.05966"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.745"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","unstructured":"Shuo Zhang and Krisztian Balog. 2020. Web Table Extraction Retrieval and Augmentation: A Survey. https:\/\/doi.org\/10.48550\/ARXIV.2002.00207","DOI":"10.48550\/ARXIV.2002.00207"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","unstructured":"Shun Zhang Zhenfang Chen Yikang Shen Mingyu Ding Joshua B. Tenenbaum and Chuang Gan. 2023. Planning with Large Language Models for Code Generation. https:\/\/doi.org\/10.48550\/arXiv.2303.05510 arXiv:2303.05510 [cs]","DOI":"10.48550\/arXiv.2303.05510"}],"event":{"name":"WSDM '24: The 17th ACM International Conference on Web Search and Data Mining","location":"Merida Mexico","acronym":"WSDM '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 17th ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635752","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3616855.3635752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:47:40Z","timestamp":1755823660000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,4]]},"references-count":42,"alternative-id":["10.1145\/3616855.3635752","10.1145\/3616855"],"URL":"https:\/\/doi.org\/10.1145\/3616855.3635752","relation":{},"subject":[],"published":{"date-parts":[[2024,3,4]]},"assertion":[{"value":"2024-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}