{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:03:53Z","timestamp":1784138633703,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":30,"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\/3805712.3809958","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"4016-4021","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Pretraining Exposure Explains Popularity Judgments in Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4850-9239","authenticated-orcid":false,"given":"Jamshid","family":"Mozafari","sequence":"first","affiliation":[{"name":"University of Innsbruck, Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3578-2393","authenticated-orcid":false,"given":"Bhawna","family":"Piryani","sequence":"additional","affiliation":[{"name":"University of Innsbruck, Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7235-0665","authenticated-orcid":false,"given":"Adam","family":"Jatowt","sequence":"additional","affiliation":[{"name":"University of Innsbruck, Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.5"},{"key":"e_1_3_2_1_3_1","first-page":"324","article-title":"Rank Analysis of Incomplete Block Designs","volume":"39","author":"Bradley Ralph Allan","year":"1952","unstructured":"Ralph Allan Bradley and Milton E. Terry. 1952. Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons. Biometrika, Vol. 39, 3\/4 (1952), 324-345. http:\/\/www.jstor.org\/stable\/2334029","journal-title":"I. The Method of Paired Comparisons. Biometrika"},{"key":"e_1_3_2_1_4_1","unstructured":"Nicholas Carlini Florian Tramer Eric Wallace Matthew Jagielski Ariel Herbert-Voss Katherine Lee Adam Roberts Tom Brown Dawn Song Ulfar Erlingsson et al. 2021. Extracting training data from large language models. In 30th USENIX security symposium (USENIX Security 21). 2633-2650."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.98"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357713.3384290"},{"key":"e_1_3_2_1_7_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_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.67"},{"key":"e_1_3_2_1_9_1","unstructured":"Saurav Kadavath Tom Conerly Amanda Askell Tom Henighan Dawn Drain Ethan Perez Nicholas Schiefer Zac Hatfield-Dodds Nova DasSarma Eli Tran-Johnson et al. 2022. Language models (mostly) know what they know. arXiv preprint arXiv:2207.05221 (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"Steven Schockaert, and Stefan Wermter.","author":"Lehmann Hans Hergen","year":"2025","unstructured":"Hans Hergen Lehmann, Jae Hee Lee, Steven Schockaert, and Stefan Wermter. 2025. Knowing the Facts but Choosing the Shortcut: Understanding How Large Language Models Compare Entities. arXiv preprint arXiv:2510.16815 (2025)."},{"key":"e_1_3_2_1_11_1","volume-title":"First Conference on Language Modeling.","author":"Liu Jiacheng","unstructured":"Jiacheng Liu, Sewon Min, Luke Zettlemoyer, Yejin Choi, and Hannaneh Hajishirzi. [n.d.]. Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens. In First Conference on Language Modeling."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.546"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597307"},{"key":"e_1_3_2_1_14_1","unstructured":"Team Olmo Allyson Ettinger Amanda Bertsch Bailey Kuehl David Graham David Heineman Dirk Groeneveld Faeze Brahman Finbarr Timbers Hamish Ivison et al. 2025. Olmo 3. arXiv preprint arXiv:2512.13961 (2025)."},{"key":"e_1_3_2_1_15_1","volume-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: an imperative style, high-performance deep learning library. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-025-11162-0"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.348"},{"key":"e_1_3_2_1_19_1","volume-title":"Detecting pretraining data from large language models. arXiv preprint arXiv:2310.16789","author":"Shi Weijia","year":"2023","unstructured":"Weijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, and Luke Zettlemoyer. 2023. Detecting pretraining data from large language models. arXiv preprint arXiv:2310.16789 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.27"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.840"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.2307\/1412159"},{"key":"e_1_3_2_1_23_1","volume-title":"Juliette Love, et al.","author":"Team Gemma","year":"2024","unstructured":"Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivi\u00e8re, Mihir Sanjay Kale, Juliette Love, et al., 2024. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-97144-0_14"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1013"},{"key":"e_1_3_2_1_26_1","volume-title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations.","author":"Wang Xuezhi","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. [n.d.]. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_28_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.conll-1.10"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.300"}],"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":"2026-07-15T17:10:06Z","timestamp":1784135406000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809958"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":30,"alternative-id":["10.1145\/3805712.3809958","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809958","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"}}]}}