{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:48:35Z","timestamp":1755794915766,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709421","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:42:22Z","timestamp":1743792142000},"page":"2292-2302","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Synthetic Survey Data Generation and Evaluation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9308-2310","authenticated-orcid":false,"given":"Yanru","family":"Jiang","sequence":"first","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7888-7373","authenticated-orcid":false,"given":"Siyu","family":"Liang","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7526-991X","authenticated-orcid":false,"given":"Junwon","family":"Choi","sequence":"additional","affiliation":[{"name":"University of California, Davis, Davis, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1017\/pan.2023.2"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422554"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1017\/pan.2024.5"},{"key":"e_1_3_2_2_4_1","unstructured":"Bauke Brenninkmeijer. 2024. Baukebrenninkmeijer\/table-evaluator. https:\/\/github.com\/Baukebrenninkmeijer\/table-evaluator original-date: 2019-08--24T14:33:20Z."},{"key":"e_1_3_2_2_5_1","unstructured":"Zhixuan Chu Hongyan Hao Xin Ouyang Simeng Wang Yan Wang Yue Shen Jinjie Gu Qing Cui Longfei Li Siqiao Xue James Y Zhang and Sheng Li. 2023. Leveraging Large Language Models for Pre-trained Recommender Systems. arXiv:2308.10837 [cs.IR]"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--88942--5_22"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3144765"},{"key":"e_1_3_2_2_8_1","unstructured":"DataCebo Inc. 2023. Synthetic Data Metrics. DataCebo Inc. https:\/\/docs.sdv.dev\/sdmetrics\/ Version 0.12.0."},{"key":"e_1_3_2_2_9_1","unstructured":"Ricardo Dominguez-Olmedo Moritz Hardt and Celestine Mendler-D\u00fcnner. 2024. Questioning the Survey Responses of Large Language Models. http:\/\/arxiv.org\/abs\/2306.07951 arXiv:2306.07951 [cs]."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-13945-1_16"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--13945--1_16"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Matteo Fabbri Guillem Bras\u00f3 Gianluca Maugeri Orcun Cetintas Riccardo Gasparini Aljo\u0161a O\u0161ep Simone Calderara Laura Leal-Taix\u00e9 and Rita Cucchiara. 2021. MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking? 10849--10859. https:\/\/openaccess.thecvf.com\/content\/ICCV2021\/html\/Fabbri_MOTSynth_How_Can_Synthetic_Data_Help_Pedestrian_Detection_ and_Tracking_ICCV_2021_paper.html","DOI":"10.1109\/ICCV48922.2021.01067"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/math10152733"},{"key":"e_1_3_2_2_14_1","unstructured":"Ian J. Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in neural information processing systems. 2672--2680."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Jie Huang and Kevin Chen-Chuan Chang. 2023. Towards Reasoning in Large Language Models: A Survey. arXiv:2212.10403 [cs.CL]","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"volume-title":"PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID: 53342261","author":"Jordon James","key":"e_1_3_2_2_16_1","unstructured":"James Jordon, Jinsung Yoon, and Mihaela van der Schaar. 2018. PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID: 53342261"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1198\/000313006X124640"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1017\/pan.2023.20"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-024-01081--4"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.8"},{"key":"e_1_3_2_2_21_1","unstructured":"Yingzhou Lu Minjie Shen Huazheng Wang Xiao Wang Capucine van Rechem Tianfan Fu and Wenqi Wei. 2024. Machine Learning for Synthetic Data Generation: A Review. http:\/\/arxiv.org\/abs\/2302.04062 arXiv:2302.04062 [cs]."},{"key":"e_1_3_2_2_22_1","unstructured":"Milad Nasr Nicholas Carlini Jonathan Hayase Matthew Jagielski A. Feder Cooper Daphne Ippolito Christopher A. Choquette-Choo Eric Wallace Florian Tram\u00e8r and Katherine Lee. 2023. Scalable Extraction of Training Data from (Production) Language Models. arXiv:2311.17035 [cs.LG]"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v074.i11"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v074.i11"},{"key":"e_1_3_2_2_25_1","first-page":"1701","article-title":"Broken promises of privacy: Responding to the surprising failure of anonymization. UCLA l","volume":"57","author":"Ohm Paul","year":"2009","unstructured":"Paul Ohm. 2009. Broken promises of privacy: Responding to the surprising failure of anonymization. UCLA l. Rev. 57 (2009), 1701.","journal-title":"Rev."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2016.49"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1068\/a38335"},{"key":"e_1_3_2_2_28_1","unstructured":"Zhaozhi Qian Bogdan-Constantin Cebere and Mihaela van der Schaar. 2023. Synthcity: facilitating innovative use cases of synthetic data in different data modalities. http:\/\/arxiv.org\/abs\/2301.07573 arXiv:2301.07573 [cs]."},{"key":"e_1_3_2_2_29_1","volume-title":"Synthetic data. Annual review of statistics and its application 8","author":"Raghunathan Trivellore E","year":"2021","unstructured":"Trivellore E Raghunathan. 2021. Synthetic data. Annual review of statistics and its application 8 (2021), 129--140."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-040720-031848"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/make4020022"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053008"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/rssa.12358"},{"key":"e_1_3_2_2_34_1","volume-title":"Solatorio and Olivier Dupriez","author":"Aivin","year":"2023","unstructured":"Aivin V. Solatorio and Olivier Dupriez. 2023. REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers. arXiv:2302.02041 [cs.LG]"},{"key":"e_1_3_2_2_35_1","unstructured":"Jennifer Taub Mark Elliot and JosephWSakshaug. 2020. The Impact of Synthetic Data Generation on Data Utility with Application to the 1991 UK Samples of Anonymised Records. (2020)."},{"key":"e_1_3_2_2_36_1","unstructured":"UCLA Library. 2023. L2 National Voter File. https:\/\/redivis.com\/datasets\/4r1cd6j182y87? v=1.1"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1111\/coin.12427"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2020.1730426"},{"key":"e_1_3_2_2_39_1","volume-title":"Examples of easy-to-implement, widely used methods of masking for which analytic properties are not justified. Statistics Research Division","author":"Winkler William E","year":"2007","unstructured":"William E Winkler. 2007. Examples of easy-to-implement, widely used methods of masking for which analytic properties are not justified. Statistics Research Division, US Bureau of the Census (2007). http:\/\/www.census.gov.edgekey.net\/srd\/papers\/pdf\/rrs2007--21.pdf."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.v1i1"},{"key":"e_1_3_2_2_41_1","unstructured":"Lei Xu Maria Skoularidou Alfredo Cuesta-Infante and Kalyan Veeramachaneni. 2019. Modeling Tabular data using Conditional GAN. In Neural Information Processing Systems. https:\/\/api.semanticscholar.org\/CorpusID:195767064"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00103"},{"key":"e_1_3_2_2_43_1","volume-title":"Robert Birke, and Lydia Y. Chen.","author":"Zhao Zilong","year":"2021","unstructured":"Zilong Zhao, Aditya Kunar, Hiek Van der Scheer, Robert Birke, and Lydia Y. Chen. 2021. CTAB-GAN: Effective Table Data Synthesizing. arXiv:2102.08369 [cs.LG]"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709421","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:36:25Z","timestamp":1755358585000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709421"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":43,"alternative-id":["10.1145\/3690624.3709421","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709421","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}