{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:11:58Z","timestamp":1765505518516,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3760916","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:36:36Z","timestamp":1762562196000},"page":"5273-5278","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating Differentially Private Generation of Domain-Specific Text"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3607-4963","authenticated-orcid":false,"given":"Yidan","family":"Sun","sequence":"first","affiliation":[{"name":"Imperial College London, Imperial Global Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6391-2950","authenticated-orcid":false,"given":"Viktor","family":"Schlegel","sequence":"additional","affiliation":[{"name":"Imperial College London, Imperial Global Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1871-4531","authenticated-orcid":false,"given":"Srinivasan","family":"Kolumam Nandakumar","sequence":"additional","affiliation":[{"name":"Imperial College London, Imperial Global Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3969-7058","authenticated-orcid":false,"given":"Iqra","family":"Zahid","sequence":"additional","affiliation":[{"name":"Imperial College London, Imperial Global Singapore, Singapore, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6399-9710","authenticated-orcid":false,"given":"Yuping","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Manchester, Manchester, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3307-9432","authenticated-orcid":false,"given":"Warren","family":"Del-Pinto","sequence":"additional","affiliation":[{"name":"University of Manchester, Manchester, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0795-5363","authenticated-orcid":false,"given":"Goran","family":"Nenadic","sequence":"additional","affiliation":[{"name":"University of Manchester, Manchester, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8346-2635","authenticated-orcid":false,"given":"Lam","family":"Siew Kei","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4230-1077","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"A*STAR, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8808-2714","authenticated-orcid":false,"given":"Anil","family":"Bharath","sequence":"additional","affiliation":[{"name":"Imperial Global Singapore, Imperial College London, London, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_1_2_1","volume-title":"Private prediction for large-scale synthetic text generation. arXiv preprint arXiv:2407.12108","author":"Amin Kareem","year":"2024","unstructured":"Kareem Amin, Alex Bie, Weiwei Kong, Alexey Kurakin, Natalia Ponomareva, Umar Syed, Andreas Terzis, and Sergei Vassilvitskii. 2024. Private prediction for large-scale synthetic text generation. arXiv preprint arXiv:2407.12108 (2024)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv585"},{"key":"e_1_3_2_1_4_1","volume-title":"METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. 65-72 pages. https:\/\/aclanthology.org\/W05-0909\/","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. 65-72 pages. https:\/\/aclanthology.org\/W05-0909\/"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.187"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_16"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34518"},{"key":"e_1_3_2_1_8_1","unstructured":"John Blitzer Mark Dredze and Fernando Pereira. 2007. Biographies Bollywood Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification. 440-447 pages. https:\/\/aclanthology.org\/P07-1056\/"},{"key":"e_1_3_2_1_9_1","volume-title":"PubMed: the bibliographic database. The NCBI handbook","author":"Canese Kathi","year":"2013","unstructured":"Kathi Canese and Sarah Weis. 2013. PubMed: the bibliographic database. The NCBI handbook, Vol. 2, 1 (2013)."},{"key":"e_1_3_2_1_10_1","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, Alina Oprea, and Colin Raffel. 2021. Extracting Training Data from Large Language Models. In 30th USENIX Security Symposium (USENIX Security 21). 2633-2650. http:\/\/arxiv.org\/abs\/2012.07805"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2029"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the IEEE Conference on Artificial Intelligence. arXiv:2207","author":"Chundawat Vikram S","year":"2022","unstructured":"Vikram S Chundawat, Ayush K Tarun, Murari Mandal, Mukund Lahoti, and Pratik Narang. 2022. TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Data. In Proceedings of the IEEE Conference on Artificial Intelligence. arXiv:2207.05295v2."},{"key":"e_1_3_2_1_13_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et al. 2021. Training Verifiers to Solve Math Word Problems. arXiv:2110.14168 (10 2021). https:\/\/arxiv.org\/abs\/2110.14168v2"},{"key":"e_1_3_2_1_14_1","volume-title":"Singapore","author":"Personal Data Protection Commission","year":"2023","unstructured":"Personal Data Protection Commission. 2023. Proposed Guide on Synthetic Data Generation. Personal Data Protection Commission, Singapore (2023)."},{"key":"e_1_3_2_1_15_1","unstructured":"Daniel-ML. 2023. Sentiment Analysis for Financial News v2. https:\/\/huggingface.co\/datasets\/Daniel-ML\/sentiment-analysis-for-financial-news-v2. Accessed: 2025-05-22."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4573321"},{"key":"e_1_3_2_1_17_1","first-page":"847","volume-title":"PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing. In 33rd USENIX Security Symposium (USENIX Security 24)","author":"Deng Gelei","year":"2024","unstructured":"Gelei Deng, Yi Liu, V\u00edctor Mayoral-Vilches, Peng Liu, Yuekang Li, Yuan Xu, Tianwei Zhang, Yang Liu, Martin Pinzger, and Stefan Rass. 2024. PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing. In 33rd USENIX Security Symposium (USENIX Security 24). USENIX Association, Philadelphia, PA, 847-864. https:\/\/www.usenix.org\/conference\/usenixsecurity24\/presentation\/deng"},{"volume-title":"Differential Privacy","author":"Dwork Cynthia","key":"e_1_3_2_1_18_1","unstructured":"Cynthia Dwork. 2006. Differential Privacy. In Automata, Languages and Programming, Michele Bugliesi, Bart Preneel, Vladimiro Sassone, and Ingo Wegener (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 1-12."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.689"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.247"},{"key":"e_1_3_2_1_21_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Yves Alexandre de Montjoye. 2023. Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) Vol. 14398 LNCS (7 2023) 182-198. doi:10.1007\/978-3-031-54204-6-10","DOI":"10.1007\/978-3-031-54204-6-10"},{"volume-title":"The jargon of the professions","author":"Hudson Kenneth","key":"e_1_3_2_1_23_1","unstructured":"Kenneth Hudson. 1978. The jargon of the professions. Springer."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/S41597-022-01899-X"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"e_1_3_2_1_26_1","volume-title":"Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy. arXiv preprint arXiv:2412.04697","author":"Koga Tatsuki","year":"2024","unstructured":"Tatsuki Koga, Ruihan Wu, and Kamalika Chaudhuri. 2024. Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy. arXiv preprint arXiv:2412.04697 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24861-0_22"},{"key":"e_1_3_2_1_28_1","unstructured":"Hao Li Yuping Wu Viktor Schlegel Riza Batista-Navarro Thanh-Tung Nguyen"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.323"},{"key":"e_1_3_2_1_30_1","volume-title":"The limits of word level differential privacy. arXiv preprint arXiv:2205.02130","author":"Mattern Justus","year":"2022","unstructured":"Justus Mattern, Benjamin Weggenmann, and Florian Kerschbaum. 2022b. The limits of word level differential privacy. arXiv preprint arXiv:2205.02130 (2022)."},{"key":"e_1_3_2_1_31_1","volume-title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text. arXiv preprint arXiv:2502.14921","author":"Meeus Matthieu","year":"2025","unstructured":"Matthieu Meeus, Lukas Wutschitz, Santiago Zanella-B\u00e9guelin, Shruti Tople, and Reza Shokri. 2025a. The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text. arXiv preprint arXiv:2502.14921 (2025)."},{"key":"e_1_3_2_1_32_1","volume-title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text. (2","author":"Meeus Matthieu","year":"2025","unstructured":"Matthieu Meeus, Lukas Wutschitz, Santiago Zanella-B\u00e9guelin, Shruti Tople, and Reza Shokri. 2025b. The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text. (2 2025). https:\/\/arxiv.org\/abs\/2502.14921v1"},{"key":"e_1_3_2_1_33_1","volume-title":"Arun-Kumar Kaliya-Perumal, Guna Pratheep Kalanchiam, Yili Tang, and Robby T. Tan.","author":"Nagar Aishik","year":"2024","unstructured":"Aishik Nagar, Yutong Liu, Andy T. Liu, Viktor Schlegel, Vijay Prakash Dwivedi, Arun-Kumar Kaliya-Perumal, Guna Pratheep Kalanchiam, Yili Tang, and Robby T. Tan. 2024. uMedSum: A Unified Framework for Advancing Medical Abstractive Summarization. (8 2024). https:\/\/arxiv.org\/abs\/2408.12095v2"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Aishik Nagar Viktor Schlegel Thanh-Tung Nguyen Hao Li Yuping Wu Kuluhan Binici and Stefan Winkler. 2025. LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction. 106-120 pages. https:\/\/aclanthology.org\/2025.insights-1.11\/","DOI":"10.18653\/v1\/2025.insights-1.11"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-ACL.285"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34678"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Sebastian Ochs and Ivan Habernal. 2025. Private Synthetic Text Generation with Diffusion Models. 10612-10626 pages. https:\/\/aclanthology.org\/2025.naacl-long.532\/","DOI":"10.18653\/v1\/2025.naacl-long.532"},{"key":"e_1_3_2_1_38_1","volume-title":"Scalable Private Learning with PATE. In International Conference on Learning Representations. http:\/\/arxiv.org\/abs\/1802","author":"Papernot Nicolas","year":"2018","unstructured":"Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, and ?\u00f6lfar Erlingsson. 2018. Scalable Private Learning with PATE. In International Conference on Learning Representations. http:\/\/arxiv.org\/abs\/1802.08908"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_40_1","first-page":"4816","article-title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","volume":"34","author":"Pillutla Krishna","year":"2021","unstructured":"Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Sean Welleck, Yejin Choi, Zaid Harchaoui, and Paul G Allen. 2021. MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers. In Advances in Neural Information Processing Systems, Vol. 34. 4816-4828. https:\/\/github.com\/krishnap25\/mauve.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","volume-title":"Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead. (3","author":"Schlegel Viktor","year":"2025","unstructured":"Viktor Schlegel, Anil A Bharath, Zilong Zhao, and Kevin Yee. 2025. Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead. (3 2025). https:\/\/arxiv.org\/abs\/2503.20846v1"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488502001648"},{"key":"e_1_3_2_1_43_1","volume-title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining. 48453-48467 pages. https:\/\/proceedings.mlr","author":"Tram\u00e8r Florian","year":"2024","unstructured":"Florian Tram\u00e8r, Gautam Kamath, and Nicholas Carlini. 2024. Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining. 48453-48467 pages. https:\/\/proceedings.mlr.press\/v235\/tramer24a.html"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M3115"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3694313"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.ACL-LONG.74"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1904.09675"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.12.005"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3760916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:08:39Z","timestamp":1765505319000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3760916"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":48,"alternative-id":["10.1145\/3746252.3760916","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3760916","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}