{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,9]],"date-time":"2026-08-09T15:50:13Z","timestamp":1786290613281,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671602","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"5476-5486","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["GRAM: Generative Retrieval Augmented Matching of Data Schemas in the Context of Data Security"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3988-5690","authenticated-orcid":false,"given":"Xuanqing","family":"Liu","sequence":"first","affiliation":[{"name":"Amazon Web Services, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0823-5982","authenticated-orcid":false,"given":"Runhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9063-9426","authenticated-orcid":false,"given":"Yang","family":"Song","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3960-4992","authenticated-orcid":false,"given":"Luyang","family":"Kong","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"[n. d.]. Software: COMA 3.0 | Database Group Leipzig. https:\/\/dbs.uni-leipzig.de\/ research\/projects\/coma."},{"key":"e_1_3_2_2_2_1","unstructured":"[n. d.]. Using BizTalk Mapper. https:\/\/learn.microsoft.com\/en-us\/biztalk\/core\/ using-biztalk-mapper. Last updated: 02\/01\/2021."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066157.1066283"},{"key":"e_1_3_2_2_4_1","unstructured":"A Chowdhery S Narang J Devlin M Bosma G Mishra A Roberts P Barham HW Chung C Sutton S Gehrmann et al. 2022. PaLM: Scaling Language Modeling with Pathways (No. arXiv: 2204.02311). arXiv."},{"key":"e_1_3_2_2_5_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_2_6_1","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems, Vol. 35 (2022), 16344--16359.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_7_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR, Vol. abs\/1810.04805 (2018). arxiv: 1810.04805 http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_2_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-155860869-6\/50060-3"},{"key":"e_1_3_2_2_10_1","unstructured":"AnHai Doan Pedro M Domingos and Alon Y Levy. 2000. Learning Source Description for Data Integration.. In WebDB (informal proceedings). 81--86."},{"key":"e_1_3_2_2_11_1","volume-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323","author":"Frantar Elias","year":"2022","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2022. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323 (2022)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-25956-5_5"},{"key":"e_1_3_2_2_13_1","volume-title":"It's AI Match: A Two-Step Approach for Schema Matching Using Embeddings. arXiv preprint arXiv:2203.04366","author":"H\u00e4ttasch Benjamin","year":"2022","unstructured":"Benjamin H\u00e4ttasch, Michael Truong-Ngoc, Andreas Schmidt, and Carsten Binnig. 2022. It's AI Match: A Two-Step Approach for Schema Matching Using Embeddings. arXiv preprint arXiv:2203.04366 (2022)."},{"key":"e_1_3_2_2_14_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_2_16_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Leviathan Yaniv","year":"2023","unstructured":"Yaniv Leviathan, Matan Kalman, and Yossi Matias. 2023. Fast inference from transformers via speculative decoding. In International Conference on Machine Learning. PMLR, 19274--19286."},{"key":"e_1_3_2_2_17_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, Vol. 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981314"},{"key":"e_1_3_2_2_19_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_20_1","volume-title":"Yi Tay, Denny Zhou, Quoc V Le, Barret Zoph, Jason Wei, et al.","author":"Longpre Shayne","year":"2023","unstructured":"Shayne Longpre, Le Hou, Tu Vu, Albert Webson, Hyung Won Chung, Yi Tay, Denny Zhou, Quoc V Le, Barret Zoph, Jason Wei, et al. 2023. The flan collection: Designing data and methods for effective instruction tuning. arXiv preprint arXiv:2301.13688 (2023)."},{"key":"e_1_3_2_2_21_1","volume-title":"Generic schema matching with cupid. In vldb","author":"Madhavan Jayant","unstructured":"Jayant Madhavan, Philip A Bernstein, and Erhard Rahm. 2001. Generic schema matching with cupid. In vldb, Vol. 1. 49--58."},{"key":"e_1_3_2_2_22_1","first-page":"49","article-title":"Evolution of the COMA match system","volume":"49","author":"Massmann Sabine","year":"2011","unstructured":"Sabine Massmann, Salvatore Raunich, David Aum\u00fcller, Patrick Arnold, Erhard Rahm, et al. 2011. Evolution of the COMA match system. Ontology Matching, Vol. 49 (2011), 49--60.","journal-title":"Ontology Matching"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2002.994702"},{"key":"e_1_3_2_2_24_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, Vol. 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_25_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s007780100057"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPIN48934.2020.9071272"},{"key":"e_1_3_2_2_28_1","volume-title":"Accelerating Transformer Inference for Translation via Parallel Decoding. arXiv preprint arXiv:2305.10427","author":"Santilli Andrea","year":"2023","unstructured":"Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin, and Emanuele Rodol\u00e0. 2023. Accelerating Transformer Inference for Translation via Parallel Decoding. arXiv preprint arXiv:2305.10427 (2023)."},{"key":"e_1_3_2_2_29_1","unstructured":"Amazon Web Services. 2023. AWS Bedrock. https:\/\/aws.amazon.com\/bedrock\/. [Online;]."},{"key":"e_1_3_2_2_30_1","volume-title":"A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on Danish commons. Biologiske skrifter","author":"Sorensen Thorvald","year":"1948","unstructured":"Thorvald Sorensen. 1948. A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on Danish commons. Biologiske skrifter, Vol. 5 (1948), 1--34."},{"key":"e_1_3_2_2_31_1","volume-title":"Sharan Narang, Dani Yogatama, Ashish Vaswani, and Donald Metzler.","author":"Tay Yi","year":"2021","unstructured":"Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, and Donald Metzler. 2021. Scale efficiently: Insights from pre-training and fine-tuning transformers. arXiv preprint arXiv:2109.10686 (2021)."},{"key":"e_1_3_2_2_32_1","first-page":"03","volume-title":"Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL","author":"Erik","year":"2003","unstructured":"Erik F. Tjong Kim Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003. 142--147. https:\/\/www.aclweb.org\/anthology\/W03-0419"},{"key":"e_1_3_2_2_33_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_34_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)."},{"key":"e_1_3_2_2_35_1","volume-title":"International Conference on Machine Learning. PMLR, 38087--38099","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2023. Smoothquant: Accurate and efficient post-training quantization for large language models. In International Conference on Machine Learning. PMLR, 38087--38099."},{"key":"e_1_3_2_2_36_1","volume-title":"mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00123"},{"key":"e_1_3_2_2_38_1","volume-title":"Universalner: Targeted distillation from large language models for open named entity recognition. arXiv preprint arXiv:2308.03279","author":"Zhou Wenxuan","year":"2023","unstructured":"Wenxuan Zhou, Sheng Zhang, Yu Gu, Muhao Chen, and Hoifung Poon. 2023. Universalner: Targeted distillation from large language models for open named entity recognition. arXiv preprint arXiv:2308.03279 (2023)."},{"key":"e_1_3_2_2_39_1","volume-title":"Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba.","author":"Zhou Yongchao","year":"2022","unstructured":"Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. 2022. Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910 (2022)."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","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 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671602","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:59Z","timestamp":1750291559000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671602"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":39,"alternative-id":["10.1145\/3637528.3671602","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671602","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}