{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:17:59Z","timestamp":1783095479192,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:00:00Z","timestamp":1718323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["845638"],"award-info":[{"award-number":["845638"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2008295"],"award-info":[{"award-number":["2008295"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2106197"],"award-info":[{"award-number":["2106197"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2103794"],"award-info":[{"award-number":["2103794"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2312991"],"award-info":[{"award-number":["2312991"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Amazon"},{"name":"Adobe"},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,14]]},"DOI":"10.1145\/3665939.3665957","type":"proceedings-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T13:22:04Z","timestamp":1718716924000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Cocoon: Semantic Table Profiling Using Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6613-0337","authenticated-orcid":false,"given":"Zezhou","family":"Huang","sequence":"first","affiliation":[{"name":"Columbia University, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4254-6688","authenticated-orcid":false,"given":"Eugene","family":"Wu","sequence":"additional","affiliation":[{"name":"Columbia University, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Yuanzhi Li, Scott Lundberg, et al.","author":"Bubeck S\u00e9bastien","year":"2023","unstructured":"S\u00e9bastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. 2023. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536258.2536262"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544847"},{"key":"e_1_3_2_1_4_1","volume-title":"From visual data exploration to visual data mining: A survey","author":"Ferreira De Oliveira MC","year":"2003","unstructured":"MC Ferreira De Oliveira and Haim Levkowitz. 2003. From visual data exploration to visual data mining: A survey. IEEE transactions on visualization and computer graphics 9, 3 (2003), 378--394."},{"key":"e_1_3_2_1_5_1","volume-title":"A formal framework for probabilistic unclean databases. arXiv preprint arXiv:1801.06750","author":"Sa Christopher De","year":"2018","unstructured":"Christopher De Sa, Ihab F Ilyas, Benny Kimelfeld, Christopher R\u00e9, and Theodoros Rekatsinas. 2018. A formal framework for probabilistic unclean databases. arXiv preprint arXiv:1801.06750 (2018)."},{"key":"e_1_3_2_1_6_1","volume-title":"LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models. arXiv preprint arXiv:2303.02927","author":"Dibia Victor","year":"2023","unstructured":"Victor Dibia. 2023. LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models. arXiv preprint arXiv:2303.02927 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Data quality and the bottom line. TDWI Report","author":"Eckerson Wayne W","year":"2002","unstructured":"Wayne W Eckerson. 2002. Data quality and the bottom line. TDWI Report, The Data Warehouse Institute (2002), 1--32."},{"key":"e_1_3_2_1_8_1","volume-title":"Dead or alive: Continuous data profiling for interactive data science","author":"Epperson Will","year":"2023","unstructured":"Will Epperson, Vaishnavi Gorantla, Dominik Moritz, and Adam Perer. 2023. Dead or alive: Continuous data profiling for interactive data science. IEEE Transactions on Visualization and Computer Graphics (2023)."},{"key":"e_1_3_2_1_9_1","first-page":"1","article-title":"Data quality considerations for big data and machine learning: Going beyond data cleaning and transformations","volume":"10","author":"Gudivada Venkat","year":"2017","unstructured":"Venkat Gudivada, Amy Apon, and Junhua Ding. 2017. Data quality considerations for big data and machine learning: Going beyond data cleaning and transformations. International Journal on Advances in Software 10, 1 (2017), 1--20.","journal-title":"International Journal on Advances in Software"},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Quantitative data cleaning for large databases","volume":"25","author":"Hellerstein Joseph M","year":"2008","unstructured":"Joseph M Hellerstein. 2008. Quantitative data cleaning for large databases. United Nations Economic Commission for Europe (UNECE) 25 (2008), 1--42.","journal-title":"United Nations Economic Commission for Europe (UNECE)"},{"key":"e_1_3_2_1_11_1","volume-title":"NeurIPS 2023 Second Table Representation Learning Workshop.","author":"Huang Zezhou","year":"2023","unstructured":"Zezhou Huang, Pavan Kalyan Damalapati, and Eugene Wu. 2023. Data Ambiguity Strikes Back: How Documentation Improves GPT's Text-to-SQL. In NeurIPS 2023 Second Table Representation Learning Workshop."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517854"},{"key":"e_1_3_2_1_13_1","volume-title":"Relationalizing Tables with Large Language Models: The Promise and Challenges. In 2024 IEEE 40th International Conference on Data Engineering Workshops (ICDEW). IEEE.","author":"Huang Zezhou","year":"2024","unstructured":"Zezhou Huang and Eugene Wu. 2024. Relationalizing Tables with Large Language Models: The Promise and Challenges. In 2024 IEEE 40th International Conference on Data Engineering Workshops (ICDEW). IEEE."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2731084"},{"key":"e_1_3_2_1_15_1","unstructured":"Hassan M Jannah. 2014. MetaReader: A Dataset Meta-Exploration and Documentation Tool."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2254556.2254659"},{"key":"e_1_3_2_1_17_1","volume-title":"Decomposed prompting: A modular approach for solving complex tasks. arXiv preprint arXiv:2210.02406","author":"Khot Tushar","year":"2022","unstructured":"Tushar Khot, Harsh Trivedi, Matthew Finlayson, Yao Fu, Kyle Richardson, Peter Clark, and Ashish Sabharwal. 2022. Decomposed prompting: A modular approach for solving complex tasks. arXiv preprint arXiv:2210.02406 (2022)."},{"key":"e_1_3_2_1_18_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2018.12.001"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 346--352","author":"Ma Pingchuan","year":"2023","unstructured":"Pingchuan Ma, Rui Ding, Shuai Wang, Shi Han, and Dongmei Zhang. 2023. InsightPilot: An LLM-Empowered Automated Data Exploration System. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 346--352."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324956"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2590989.2590995"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2100--2109","author":"Qahtan Abdulhakim A","year":"2018","unstructured":"Abdulhakim A Qahtan, Ahmed Elmagarmid, Raul Castro Fernandez, Mourad Ouzzani, and Nan Tang. 2018. FAHES: A robust disguised missing values detector. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2100--2109."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3320212"},{"key":"e_1_3_2_1_25_1","volume-title":"Holoclean: Holistic data repairs with probabilistic inference. arXiv preprint arXiv:1702.00820","author":"Rekatsinas Theodoros","year":"2017","unstructured":"Theodoros Rekatsinas, Xu Chu, Ihab F Ilyas, and Christopher R\u00e9. 2017. Holoclean: Holistic data repairs with probabilistic inference. arXiv preprint arXiv:1702.00820 (2017)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2945779"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocx079"},{"key":"e_1_3_2_1_29_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824--24837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","volume-title":"A protocol for data exploration to avoid common statistical problems. Methods in ecology and evolution 1, 1","author":"Zuur Alain F","year":"2010","unstructured":"Alain F Zuur, Elena N Ieno, and Chris S Elphick. 2010. A protocol for data exploration to avoid common statistical problems. Methods in ecology and evolution 1, 1 (2010), 3--14."}],"event":{"name":"HILDA 24: 2024 Workshop on Human-In-the-Loop Data Analytics","location":"Santiago AA Chile","acronym":"HILDA 24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2024 Workshop on Human-In-the-Loop Data Analytics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665939.3665957","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3665939.3665957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:27Z","timestamp":1750290267000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665939.3665957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,14]]},"references-count":30,"alternative-id":["10.1145\/3665939.3665957","10.1145\/3665939"],"URL":"https:\/\/doi.org\/10.1145\/3665939.3665957","relation":{},"subject":[],"published":{"date-parts":[[2024,6,14]]},"assertion":[{"value":"2024-06-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}