{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:07:31Z","timestamp":1784182051778,"version":"3.55.0"},"reference-count":36,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010622","name":"Hefei University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010622","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010814","name":"Department of Education of Anhui Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010814","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.asoc.2026.115939","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T12:39:11Z","timestamp":1784032751000},"page":"115939","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Beyond frequency: The role of redundancy in large language model memorization"],"prefix":"10.1016","volume":"202","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0507-4818","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinghua","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-ho","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9025-0748","authenticated-orcid":false,"given":"Zhongfeng","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2929-0828","authenticated-orcid":false,"given":"Lei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115939_bib0005","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Quantifying memorization across neural language models","author":"Carlini","year":"2023"},{"key":"10.1016\/j.asoc.2026.115939_bib0010","series-title":"Advances in Neural Information Processing Systems, 36","first-page":"28072","article-title":"Emergent and predictable memorization in large language models","author":"Biderman","year":"2023"},{"key":"10.1016\/j.asoc.2026.115939_bib0015","series-title":"30th USENIX Security Symposium (USENIX Security 21)","first-page":"2633","article-title":"Extracting training data from large language models","author":"Carlini","year":"2021"},{"key":"10.1016\/j.asoc.2026.115939_bib0020","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"7403","article-title":"Copyright violations and large language models","author":"Karamolegkou","year":"2023"},{"key":"10.1016\/j.asoc.2026.115939_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128473","article-title":"Understanding activation patterns in artificial neural networks by exploring stochastic processes: discriminating generalization from memorization","volume":"610","author":"Lehmler","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115939_bib0030","author":"Luo"},{"key":"10.1016\/j.asoc.2026.115939_bib0035","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"8424","article-title":"Deduplicating training data makes language models better","author":"Lee","year":"2022"},{"key":"10.1016\/j.asoc.2026.115939_bib0040","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Mitigating memorization in language models","author":"Sakarvadia","year":"2025"},{"key":"10.1016\/j.asoc.2026.115939_bib0045","series-title":"International Conference on Machine Learning","first-page":"10697","article-title":"Deduplicating training data mitigates privacy risks in language models","author":"Kandpal","year":"2022"},{"key":"10.1016\/j.asoc.2026.115939_bib0050","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"4360","article-title":"Preserving privacy through dememorization: an unlearning technique for mitigating memorization risks in language models","author":"Kassem","year":"2023"},{"key":"10.1016\/j.asoc.2026.115939_bib0055","series-title":"The Twelfth International Conference on Learning Representations","article-title":"Beyond memorization: violating privacy via inference with large language models","author":"Staab","year":"2024"},{"key":"10.1016\/j.asoc.2026.115939_bib0060","series-title":"Web Information Systems Engineering \u2013 WISE 2024: 25th International Conference, Doha, Qatar, December 2\u20135, 2024, Proceedings, Part II","first-page":"333","article-title":"On the alignment of group fairness with attribute privacy","author":"Aalmoes","year":"2024"},{"key":"10.1016\/j.asoc.2026.115939_bib0065","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"12216","article-title":"Dissecting recall of factual associations in auto-regressive language models","author":"Geva","year":"2023"},{"key":"10.1016\/j.asoc.2026.115939_bib0070","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"6549","article-title":"Discovering knowledge-critical subnetworks in pretrained language models","author":"Bayazit","year":"2024"},{"key":"10.1016\/j.asoc.2026.115939_bib0075","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"11740","article-title":"FastMem: fast memorization of prompt improves context awareness of large language models","author":"Zhu","year":"2024"},{"key":"10.1016\/j.asoc.2026.115939_bib0080","series-title":"Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics","first-page":"248","article-title":"Understanding transformer memorization recall through idioms","author":"Haviv","year":"2023"},{"key":"10.1016\/j.asoc.2026.115939_bib0085","author":"Huang"},{"key":"10.1016\/j.asoc.2026.115939_bib0090","author":"Bai"},{"key":"10.1016\/j.asoc.2026.115939_bib0095","series-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS \u201922","article-title":"Memorization without overfitting: analyzing the training dynamics of large language models","author":"Tirumala","year":"2022"},{"key":"10.1016\/j.asoc.2026.115939_bib0100","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"11263","article-title":"Scaling laws for fact memorization of large language models","author":"Lu","year":"2024"},{"key":"10.1016\/j.asoc.2026.115939_bib0105","series-title":"Proceedings of the 41st International Conference on Machine Learning, ICML\u201924","article-title":"Copyright traps for large language models","author":"Meeus","year":"2024"},{"issue":"8017","key":"10.1016\/j.asoc.2026.115939_bib0110","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1038\/s41586-024-07522-w","article-title":"Language is primarily a tool for communication rather than thought","volume":"630","author":"Fedorenko","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.asoc.2026.115939_bib0115","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"3190","article-title":"Do localization methods actually localize memorized data in LLMs? A tale of two benchmarks","author":"Chang","year":"2024"},{"key":"10.1016\/j.asoc.2026.115939_bib0120","series-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"10661","article-title":"Analyzing memorization in large language models through the lens of model attribution","author":"Menta","year":"2025"},{"key":"10.1016\/j.asoc.2026.115939_bib0125","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"10711","article-title":"Demystifying verbatim memorization in large language models","author":"Huang","year":"2024"},{"key":"10.1016\/j.asoc.2026.115939_bib0130","series-title":"Advances in Neural Information Processing Systems, 35","first-page":"23908","article-title":"Decoupling knowledge from memorization: retrieval-augmented prompt learning","author":"Chen","year":"2022"},{"key":"10.1016\/j.asoc.2026.115939_bib0135","series-title":"Advances in Neural Information Processing Systems, 36","first-page":"39321","article-title":"Counterfactual memorization in neural language models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.asoc.2026.115939_bib0140","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Recite, reconstruct, recollect: memorization in LMs as a multifaceted phenomenon","author":"Prashanth","year":"2025"},{"key":"10.1016\/j.asoc.2026.115939_bib0145","series-title":"Findings of the Association for Computational Linguistics: ACL 2024","first-page":"13909","article-title":"Investigating the impact of data contamination of large language models in Text-to-SQL translation","author":"Ranaldi","year":"2024"},{"key":"10.1016\/j.asoc.2026.115939_bib0150","author":"Stoehr"},{"key":"10.1016\/j.asoc.2026.115939_bib0155","author":"Xie"},{"key":"10.1016\/j.asoc.2026.115939_bib0160","author":"Gao"},{"key":"10.1016\/j.asoc.2026.115939_bib0165","series-title":"Proceedings of the 40th International Conference on Machine Learning, ICML\u201923","article-title":"Pythia: a suite for analyzing large language models across training and scaling","author":"Biderman","year":"2023"},{"key":"10.1016\/j.asoc.2026.115939_bib0170","article-title":"Finding neurons in a haystack: case studies with sparse probing","author":"Gurnee","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.asoc.2026.115939_bib0175","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"15616","article-title":"Causal estimation of memorisation profiles","author":"Lesci","year":"2024"},{"key":"10.1016\/j.asoc.2026.115939_bib0180","author":"Srivastava"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626013876?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626013876?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:30:31Z","timestamp":1784179831000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626013876"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":36,"alternative-id":["S1568494626013876"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115939","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Beyond frequency: The role of redundancy in large language model memorization","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115939","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115939"}}