{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T13:02:06Z","timestamp":1793710926958,"version":"4.6.1"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808619","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3319-3327","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Sensitivity-Aware Test Collection for Search Among Personal Information"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1509-9248","authenticated-orcid":false,"given":"Jack","family":"McKechnie","sequence":"first","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1266-5996","authenticated-orcid":false,"given":"Graham","family":"McDonald","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3143-279X","authenticated-orcid":false,"given":"Craig","family":"Macdonald","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA460118"},{"key":"e_1_3_2_1_2_1","volume-title":"Carlo Gaibisso, and Giorgio Gambosi","author":"Amati Giambattista","year":"2008","unstructured":"Giambattista Amati, Giuseppe Amodeo, Marco Bianchi, Carlo Gaibisso, and Giorgio Gambosi. 2008. FUB, IASI-CNR and University of Tor Vergata at TREC 2008 blog track. (2008)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582416"},{"key":"e_1_3_2_1_4_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Oard","author":"Baron Jason R","year":"2023","unstructured":"Jason R Baron, Nathaniel W Rollings, and Douglas W. Oard. 2023. Using ChatGPT for the FOIA Exemption 5 Deliberative Process Privilege. In LegalAIIA @ ICAIL."},{"key":"e_1_3_2_1_6_1","volume-title":"Jeff Harrold, Sarah Howell, and Jason R Baron.","author":"Branting Karl","year":"2025","unstructured":"Karl Branting, Bradford Brown, Chris Giannella, James Van Guilder, Jeff Harrold, Sarah Howell, and Jason R Baron. 2025. Decision support for detecting sensitive text in government records: Anonymous submission. AI Law, Vol. 33, 1 (2025)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23501-6_4"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657765"},{"key":"e_1_3_2_1_9_1","volume-title":"Overview of the TREC 2010 legal track. In Proc. of TREC.","author":"Cormack Gordon V","unstructured":"Gordon V Cormack, Maura R Grossman, Bruce Hedin, and Douglas W. Oard. 2010. Overview of the TREC 2010 legal track. In Proc. of TREC."},{"key":"e_1_3_2_1_10_1","unstructured":"John Dang Shivalika Singh Daniel D'souza Arash Ahmadian Alejandro Salamanca Madeline Smith Aidan Peppin Sungjin Hong Manoj Govindassamy Terrence Zhao et al. 2024. Aya expanse: Combining research breakthroughs for a new multilingual frontier. arXiv preprint arXiv:2412.04261 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Department for Business and Trade, Office for Artificial Intelligence, Department for Digital, Culture, Media & Sport, and Department for Business, Energy & Industrial Strategy.","author":"Department for Science","year":"2019","unstructured":"Department for Science, Innovation and Technology, Department for Business and Trade, Office for Artificial Intelligence, Department for Digital, Culture, Media & Sport, and Department for Business, Energy & Industrial Strategy. 2019. Artificial Intelligence Sector Deal. https:\/\/www.gov.uk\/government\/publications\/artificial-intelligence-sector-deal (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731120.3744588"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578337.3605136"},{"key":"e_1_3_2_1_14_1","volume-title":"SPLADE v2: Sparse lexical and expansion model for information retrieval. arXiv preprint arXiv:2109.10086","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Carlos Lassance, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021. SPLADE v2: Sparse lexical and expansion model for information retrieval. arXiv preprint arXiv:2109.10086 (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3634912"},{"key":"e_1_3_2_1_16_1","unstructured":"Timothy Gollins Graham McDonald Craig Macdonald and Iadh Ounis. 2014. On Using Information Retrieval for the Selection and Sensitivity Review of Digital Public Records. In PIR @ SIGIR."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Marti A Hearst. 2005. Teaching applied natural language processing: Triumphs and tribulations. In ETMTNLP @ ACL.","DOI":"10.3115\/1627291.1627293"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449207"},{"key":"e_1_3_2_1_19_1","volume-title":"access and artificial intelligence: working with born-digital and digitized archival collections","author":"Jaillant Lise","unstructured":"Lise Jaillant. 2022a. Archives, access and artificial intelligence: working with born-digital and digitized archival collections. Bielefeld University Press."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10502-022-09390-7"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-021-01367-x"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1093\/llc\/fqac073"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_24_1","volume-title":"Robertson","author":"Jones Karen Sparck","year":"2000","unstructured":"Karen Sparck Jones, Steve Walker, and Stephen E. Robertson. 2000. A probabilistic model of information retrieval: development and comparative experiments: Part 2. Vol. 36, 6 (2000)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/30.1-2.81"},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. of CEAS.","author":"Klimt Bryan","year":"2004","unstructured":"Bryan Klimt and Yiming Yang. 2004. Introducing the Enron corpus. In Proc. of CEAS."},{"key":"e_1_3_2_1_27_1","volume-title":"SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789","author":"Lassance Carlos","year":"2024","unstructured":"Carlos Lassance, Herv\u00e9 D\u00e9jean, Thibault Formal, and St\u00e9phane Clinchant. 2024. SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789 (2024)."},{"key":"e_1_3_2_1_28_1","unstructured":"Sheng-Chieh Lin Jheng-Hong Yang and Jimmy Lin. 2021. In-batch negatives for knowledge distillation with tightly-coupled teachers for dense retrieval. In RepL4NLP @ ACL."},{"key":"e_1_3_2_1_29_1","volume-title":"BMLA","volume":"88","author":"Lipscomb Carolyn E","year":"2000","unstructured":"Carolyn E Lipscomb. 2000. Medical subject headings (MeSH). BMLA, Vol. 88, 3 (2000)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730147"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463254"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28241-6_25"},{"key":"e_1_3_2_1_34_1","unstructured":"Andrew McCallum Andr\u00e9s Corrada-Emmanuel and Xuerui Wang. 2005. The author-recipient-topic model for topic and role discovery in social networks: Experiments with enron and academic email. In Online Preprint."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080731"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56608-5_35"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-76941-7_65"},{"key":"e_1_3_2_1_38_1","volume-title":"TOIS","volume":"39","author":"McDonald Graham","year":"2020","unstructured":"Graham McDonald, Craig Macdonald, and Iadh Ounis. 2020. How the accuracy and confidence of sensitivity classification affects digital sensitivity review. TOIS, Vol. 39, 1 (2020)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-06028-6_48"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56069-9_41"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657895"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-88708-6_19"},{"key":"e_1_3_2_1_43_1","volume-title":"Re-Rankers as Relevance Judges. arXiv preprint arXiv:2601.04455","author":"Meng Chuan","year":"2026","unstructured":"Chuan Meng, Jiqun Liu, Mohammad Aliannejadi, Fengran Mo, Jeff Dalton, and Maarten de Rijke. 2026. Re-Rankers as Relevance Judges. arXiv preprint arXiv:2601.04455 (2026)."},{"key":"e_1_3_2_1_44_1","volume-title":"JCAS","volume":"4","author":"Moss Michael S","year":"2017","unstructured":"Michael S Moss and Tim J Gollins. 2017. Our digital legacy: an archival perspective. JCAS, Vol. 4, 2 (2017)."},{"key":"e_1_3_2_1_45_1","volume-title":"Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, and Jimmy Lin. 2019. Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424 (2019)."},{"key":"e_1_3_2_1_46_1","volume-title":"TOIS","volume":"37","author":"Oard Douglas W.","year":"2018","unstructured":"Douglas W. Oard, Fabrizio Sebastiani, and Jyothi K Vinjumur. 2018. Jointly minimizing the expected costs of review for responsiveness and privilege in e-discovery. TOIS, Vol. 37, 1 (2018)."},{"key":"e_1_3_2_1_47_1","unstructured":"Douglas W. Oard Katie Shilton and Jimmy Lin. 2016. Evaluating Search Among Secrets. In EVIA @ NTCIR."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99736-6_44"},{"key":"e_1_3_2_1_49_1","volume-title":"The expando-mono-duo design pattern for text ranking with pretrained sequence-to-sequence models. arXiv preprint arXiv:2101.05667","author":"Pradeep Ronak","year":"2021","unstructured":"Ronak Pradeep, Rodrigo Nogueira, and Jimmy Lin. 2021. The expando-mono-duo design pattern for text ranking with pretrained sequence-to-sequence models. arXiv preprint arXiv:2101.05667 (2021)."},{"key":"e_1_3_2_1_50_1","volume-title":"Genetics","volume":"155","author":"Pritchard Jonathan K","year":"2000","unstructured":"Jonathan K Pritchard, Matthew Stephens, and Peter Donnelly. 2000. Inference of population structure using multilocus genotype data. Genetics, Vol. 155, 2 (2000)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Ronald Rivest. 1992. RFC1321: The MD5 message-digest algorithm.","DOI":"10.17487\/rfc1321"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401284"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331256"},{"key":"e_1_3_2_1_54_1","article-title":"A statistical interpretation of term specificity and its application in retrieval","volume":"28","author":"Jones Karen Sparck","year":"1972","unstructured":"Karen Sparck Jones. 1972. A statistical interpretation of term specificity and its application in retrieval. J. Doc, Vol. 28, 1 (1972).","journal-title":"J. Doc"},{"key":"e_1_3_2_1_55_1","article-title":"Information retrieval test collections","volume":"32","author":"Jones Karen Sparck","year":"1976","unstructured":"Karen Sparck Jones and Cornelis Joost Van Rijsbergen. 1976. Information retrieval test collections. J. Doc., Vol. 32, 1 (1976).","journal-title":"J. Doc."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.2307\/1412159"},{"key":"e_1_3_2_1_57_1","article-title":"The rise and fall of Enron","volume":"193","author":"Thomas C William","year":"2002","unstructured":"C William Thomas. 2002. The rise and fall of Enron. J. Account, Vol. 193, 4 (2002).","journal-title":"J. Account"},{"key":"e_1_3_2_1_58_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"Umbrela: Umbrela is the (open-source reproduction of the) bing relevance assessor. arXiv preprint arXiv:2406.06519","author":"Upadhyay Shivani","year":"2024","unstructured":"Shivani Upadhyay, Ronak Pradeep, Nandan Thakur, Nick Craswell, and Jimmy Lin. 2024. Umbrela: Umbrela is the (open-source reproduction of the) bing relevance assessor. arXiv preprint arXiv:2406.06519 (2024)."},{"key":"e_1_3_2_1_60_1","volume-title":"Proc. of ASIS&T","volume":"52","author":"Vinjumur Jyothi K","year":"2015","unstructured":"Jyothi K Vinjumur and Douglas W. Oard. 2015. Finding the privileged few: Supporting privilege review for e-discovery. Proc. of ASIS&T, Vol. 52, 1 (2015)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291017"},{"key":"e_1_3_2_1_62_1","volume-title":"Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591915"},{"key":"e_1_3_2_1_64_1","volume-title":"NeurIPS","volume":"33","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. NeurIPS, Vol. 33 (2020)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Shitao Xiao Zheng Liu Yingxia Shao and Zhao Cao. 2022. RetroMAE: Pre-training retrieval-oriented language models via masked auto-encoder. (2022).","DOI":"10.18653\/v1\/2022.emnlp-main.35"},{"key":"e_1_3_2_1_66_1","volume-title":"Proc. of ICLR.","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In Proc. of ICLR."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390435"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3392871"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:14:40Z","timestamp":1784135680000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808619"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":68,"alternative-id":["10.1145\/3805712.3808619","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808619","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}