{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:39:21Z","timestamp":1786120761898,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":54,"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-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817642","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:43Z","timestamp":1786036543000},"page":"4963-4974","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2900-7413","authenticated-orcid":false,"given":"Mengqi","family":"Wang","sequence":"first","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7887-4179","authenticated-orcid":false,"given":"Jianwei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7895-9551","authenticated-orcid":false,"given":"Qing","family":"Liu","sequence":"additional","affiliation":[{"name":"Data61, CSIRO, Sandy Bay, Tasmania, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2273-1862","authenticated-orcid":false,"given":"Xiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Data61, CSIRO, Eveleigh, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7663-1421","authenticated-orcid":false,"given":"Zhenchang","family":"Xing","sequence":"additional","affiliation":[{"name":"Data61, CSIRO, Canberra, ACT, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5839-3765","authenticated-orcid":false,"given":"Liming","family":"Zhu","sequence":"additional","affiliation":[{"name":"Data61, CSIRO, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4309-6511","authenticated-orcid":false,"given":"Michael","family":"Bain","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6572-2600","authenticated-orcid":false,"given":"Wenjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"386","article-title":"SAGED","author":"Abdelaal Mohamed","year":"2024","unstructured":"Mohamed Abdelaal, Tim Ktitarev, Daniel St\u00e4dtler, and Harald Sch\u00f6ning. 2024. SAGED: Few-Shot Meta Learning for Tabular Data Error Detection. In EDBT. 386-398.","journal-title":"Few-Shot Meta Learning for Tabular Data Error Detection. In EDBT."},{"key":"e_1_3_2_1_2_1","volume-title":"Exploring llm agents for cleaning tabular machine learning datasets. arXiv preprint arXiv:2503.06664","author":"Bendinelli Tommaso","year":"2025","unstructured":"Tommaso Bendinelli, Artur Dox, and Christian Holz. 2025. Exploring llm agents for cleaning tabular machine learning datasets. arXiv preprint arXiv:2503.06664 (2025)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157800"},{"key":"e_1_3_2_1_4_1","volume-title":"Zero-shot decision tree construction via large language models. arXiv preprint arXiv:2501.16247","author":"Carrasco Lucas","year":"2025","unstructured":"Lucas Carrasco, Felipe Urrutia, and Andr\u00e9s Abeliuk. 2025. Zero-shot decision tree construction via large language models. arXiv preprint arXiv:2501.16247 (2025)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3749174"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2912574"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2749431"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.2307\/2346806"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536274.2536280"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1412331.1412337"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/3742728.3742754"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3012472"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3470817"},{"key":"e_1_3_2_1_14_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319888"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2003"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196889"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.290"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736818"},{"key":"e_1_3_2_1_20_1","volume-title":"CORTEX: Cost-Sensitive Rule and Tree Extraction Method. Knowledge-Based Systems","author":"Kopanja Marija","year":"2025","unstructured":"Marija Kopanja, Milo\u0161 Savi\u0107, and Luca Longo. 2025. CORTEX: Cost-Sensitive Rule and Tree Extraction Method. Knowledge-Based Systems (2025), 114592."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994514"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50026-X"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685838"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00009"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.658"},{"key":"e_1_3_2_1_26_1","unstructured":"Mohammad Mahdavi and Ziawasch Abedjan. 2021. Semi-Supervised Data Cleaning with Raha and Baran.. In CIDR."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324956"},{"key":"e_1_3_2_1_28_1","first-page":"73212","volume-title":"International Conference on Learning Representations","volume":"2025","author":"Matton Katie","year":"2025","unstructured":"Katie Matton, Robert Ness, John Guttag, and Emre Kiciman. 2025. Walk the talk? measuring the faithfulness of large language model explanations. In International Conference on Learning Representations, Vol. 2025. 73212-73277."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574258"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447541"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00234"},{"key":"e_1_3_2_1_32_1","volume-title":"Schema matching with large language models: an experimental study. arXiv preprint arXiv:2407.11852","author":"Parciak Marcel","year":"2024","unstructured":"Marcel Parciak, Brecht Vandevoort, Frank Neven, Liesbet M Peeters, and Stijn Vansummeren. 2024. Schema matching with large language models: an experimental study. arXiv preprint arXiv:2407.11852 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3503585.3503595"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cjca.2021.09.004"},{"key":"e_1_3_2_1_35_1","first-page":"3543","article-title":"SPADE: A Semi-supervised Probabilistic Approach for Detecting Errors in Tables","author":"Pham Minh","year":"2021","unstructured":"Minh Pham, Craig A Knoblock, Muhao Chen, Binh Vu, and Jay Pujara. 2021. SPADE: A Semi-supervised Probabilistic Approach for Detecting Errors in Tables.. In IJCAI. 3543-3551.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_36_1","unstructured":"Clement Pit-Claudel Zelda Mariet Rachael Harding and Sam Madden. 2016. Outlier detection in heterogeneous datasets using automatic tuple expansion. (2016)."},{"key":"e_1_3_2_1_37_1","first-page":"432","volume-title":"Few-shot LLM Synthetic Data with Distribution Matching. In Companion Proceedings of the ACM on Web Conference","author":"Ren Jiyuan","year":"2025","unstructured":"Jiyuan Ren, Zhaocheng Du, Zhihao Wen, Qinglin Jia, Sunhao Dai, Chuhan Wu, and Zhenhua Dong. 2025. Few-shot LLM Synthetic Data with Distribution Matching. In Companion Proceedings of the ACM on Web Conference 2025. 432-441."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714892"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.730"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/3748191.3748205"},{"key":"e_1_3_2_1_41_1","volume-title":"Ensemble-based Deep Multilayer Community Search. arXiv preprint arXiv:2501.02194","author":"Wang Jianwei","year":"2025","unstructured":"Jianwei Wang, Yuehai Wang, Kai Wang, Xuemin Lin, Wenjie Zhang, and Ying Zhang. 2025b. Ensemble-based Deep Multilayer Community Search. arXiv preprint arXiv:2501.02194 (2025)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654920"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics. 96-109","author":"Wang Tianshu","year":"2025","unstructured":"Tianshu Wang, Xiaoyang Chen, Hongyu Lin, Xuanang Chen, Xianpei Han, Le Sun, Hao Wang, and Zhenyu Zeng. 2025a. Match, compare, or select? an investigation of large language models for entity matching. In Proceedings of the 31st International Conference on Computational Linguistics. 96-109."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3641960"},{"key":"e_1_3_2_1_45_1","volume-title":"Denny Zhou, et al.","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, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00221"},{"key":"e_1_3_2_1_47_1","volume-title":"Gptree: Towards explainable decision-making via llm-powered decision trees. arXiv preprint arXiv:2411.08257","author":"Xiong Sichao","year":"2024","unstructured":"Sichao Xiong, Yigit Ihlamur, Fuat Alican, and Aaron Ontoyin Yin. 2024. Gptree: Towards explainable decision-making via llm-powered decision trees. arXiv preprint arXiv:2411.08257 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models. In International Conference on Learning Representations (ICLR).","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_49_1","first-page":"19075","article-title":"Handling missing data with graph representation learning","volume":"33","author":"You Jiaxuan","year":"2020","unstructured":"Jiaxuan You, Xiaobai Ma, Yi Ding, Mykel J Kochenderfer, and Jure Leskovec. 2020. Handling missing data with graph representation learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 19075-19087.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695061"},{"key":"e_1_3_2_1_51_1","volume-title":"Jellyfish: A large language model for data preprocessing. arXiv preprint arXiv:2312.01678","author":"Zhang Haochen","year":"2023","unstructured":"Haochen Zhang, Yuyang Dong, Chuan Xiao, and Masafumi Oyamada. 2023. Jellyfish: A large language model for data preprocessing. arXiv preprint arXiv:2312.01678 (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW67478.2025.00008"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457289"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.14778\/3712221.3712233"}],"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":"2026-08-07T01:24:40Z","timestamp":1786065880000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817642"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":54,"alternative-id":["10.1145\/3770855.3817642","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817642","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"}}]}}