{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T09:06:56Z","timestamp":1784279216940,"version":"3.55.0"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007567","name":"City University of Hong Kong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113782","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:15:58Z","timestamp":1776442558000},"page":"113782","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["CSBoRA: A continual learning method for large language models with true orthogonality and reduced forgetting"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9661-1341","authenticated-orcid":false,"given":"Yuyang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lai-Man","family":"Po","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farrell","family":"Hung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuohan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoxuan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuyuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwok-Wai","family":"Cheung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113782_b1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"8","key":"10.1016\/j.patcog.2026.113782_b2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"10.1016\/j.patcog.2026.113782_b3","article-title":"SceneLLM: Implicit language reasoning in LLM for dynamic scene graph generation","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"issue":"12","key":"10.1016\/j.patcog.2026.113782_b4","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1038\/s42256-022-00568-3","article-title":"Three types of incremental learning","volume":"4","author":"Van de Ven","year":"2022","journal-title":"Nat. Mach. Intell."},{"issue":"8","key":"10.1016\/j.patcog.2026.113782_b5","doi-asserted-by":"crossref","first-page":"5362","DOI":"10.1109\/TPAMI.2024.3367329","article-title":"A comprehensive survey of continual learning: Theory, method and application","volume":"46","author":"Wang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113782_b6","doi-asserted-by":"crossref","unstructured":"Z. Ke, H. Lin, Y. Shao, H. Xu, L. Shu, B. Liu, Continual training of language models for few-shot learning, in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, pp. 10205\u201310216.","DOI":"10.18653\/v1\/2022.emnlp-main.695"},{"issue":"13","key":"10.1016\/j.patcog.2026.113782_b7","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"12","key":"10.1016\/j.patcog.2026.113782_b8","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113782_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110943","article-title":"Class incremental learning with self-supervised pre-training and prototype learning","volume":"157","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"issue":"2","key":"10.1016\/j.patcog.2026.113782_b10","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models.","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"10.1016\/j.patcog.2026.113782_b11","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"10658","article-title":"Orthogonal subspace learning for language model continual learning","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113782_b12","doi-asserted-by":"crossref","unstructured":"R. Po, G. Yang, K. Aberman, G. Wetzstein, Orthogonal adaptation for modular customization of diffusion models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 7964\u20137973.","DOI":"10.1109\/CVPR52733.2024.00761"},{"key":"10.1016\/j.patcog.2026.113782_b13","doi-asserted-by":"crossref","unstructured":"W. Zhao, S. Wang, Y. Hu, Y. Zhao, B. Qin, X. Zhang, Q. Yang, D. Xu, W. Che, Sapt: A shared attention framework for parameter-efficient continual learning of large language models, in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, pp. 11641\u201311661.","DOI":"10.18653\/v1\/2024.acl-long.625"},{"key":"10.1016\/j.patcog.2026.113782_b14","series-title":"International Conference on Neural Information Processing","first-page":"387","article-title":"Sbora: Low-rank adaptation with regional weight updates","author":"Po","year":"2024"},{"key":"10.1016\/j.patcog.2026.113782_b15","series-title":"On tiny episodic memories in continual learning","author":"Chaudhry","year":"2019"},{"key":"10.1016\/j.patcog.2026.113782_b16","article-title":"Episodic memory in lifelong language learning","volume":"32","author":"de Masson D\u2019Autume","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113782_b17","doi-asserted-by":"crossref","first-page":"15027","DOI":"10.52202\/075280-0660","article-title":"A unified approach to domain incremental learning with memory: Theory and algorithm","volume":"36","author":"Shi","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113782_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111093","article-title":"Continual learning with high-order experience replay for dynamic network embedding","volume":"159","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113782_b19","doi-asserted-by":"crossref","unstructured":"R. Aljundi, F. Babiloni, M. Elhoseiny, M. Rohrbach, T. Tuytelaars, Memory aware synapses: Learning what (not) to forget, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 139\u2013154.","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"10.1016\/j.patcog.2026.113782_b20","article-title":"Low-redundancy distillation for continual learning","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113782_b21","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with C-LoRA","author":"Smith","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113782_b22","unstructured":"Y.-Y. Qian, Y.-Z. Xu, Z.-Y. Zhang, P. Zhao, Z.-H. Zhou, TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree, in: Forty-Second International Conference on Machine Learning, 2025."},{"key":"10.1016\/j.patcog.2026.113782_b23","doi-asserted-by":"crossref","unstructured":"Y. Huang, Y. Zhang, J. Chen, X. Wang, D. Yang, Continual learning for text classification with information disentanglement based regularization, in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, pp. 2736\u20132746.","DOI":"10.18653\/v1\/2021.naacl-main.218"},{"key":"10.1016\/j.patcog.2026.113782_b24","doi-asserted-by":"crossref","unstructured":"Z. Wang, Z. Zhang, C.-Y. Lee, H. Zhang, R. Sun, X. Ren, G. Su, V. Perot, J. Dy, T. Pfister, Learning to prompt for continual learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 139\u2013149.","DOI":"10.1109\/CVPR52688.2022.00024"},{"issue":"140","key":"10.1016\/j.patcog.2026.113782_b25","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113782_b26","series-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.patcog.2026.113782_b27","series-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"10.1016\/j.patcog.2026.113782_b28","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby, An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.patcog.2026.113782_b29","article-title":"Character-level convolutional networks for text classification","volume":"28","author":"Zhang","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113782_b30","unstructured":"A. Razdaibiedina, Y. Mao, R. Hou, M. Khabsa, M. Lewis, A. Almahairi, Progressive Prompts: Continual Learning for Language Models, in: The Eleventh International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.patcog.2026.113782_b31","unstructured":"D. Hendrycks, C. Burns, S. Basart, A. Zou, M. Mazeika, D. Song, J. Steinhardt, Measuring Massive Multitask Language Understanding, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.patcog.2026.113782_b32","article-title":"Hide-pet: continual learning via hierarchical decomposition of parameter-efficient tuning","author":"Wang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113782_b33","doi-asserted-by":"crossref","unstructured":"A. Wang, A. Singh, J. Michael, F. Hill, O. Levy, S. Bowman, GLUE: A multi-task benchmark and analysis platform for natural language understanding, in: Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 2018, pp. 353\u2013355.","DOI":"10.18653\/v1\/W18-5446"},{"key":"10.1016\/j.patcog.2026.113782_b34","article-title":"Superglue: A stickier benchmark for general-purpose language understanding systems","volume":"32","author":"Wang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113782_b35","unstructured":"A. Maas, R.E. Daly, P.T. Pham, D. Huang, A.Y. Ng, C. Potts, Learning word vectors for sentiment analysis, in: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 2011, pp. 142\u2013150."},{"key":"10.1016\/j.patcog.2026.113782_b36","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.patcog.2026.113782_b37","doi-asserted-by":"crossref","unstructured":"D. Hendrycks, S. Basart, N. Mu, S. Kadavath, F. Wang, E. Dorundo, R. Desai, T. Zhu, S. Parajuli, M. Guo, et al., The many faces of robustness: A critical analysis of out-of-distribution generalization, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 8340\u20138349.","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"10.1016\/j.patcog.2026.113782_b38","series-title":"The caltech-ucsd birds-200\u20132011 dataset","author":"Wah","year":"2011"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007478?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007478?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T08:33:49Z","timestamp":1784277229000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326007478"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":38,"alternative-id":["S0031320326007478"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113782","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CSBoRA: A continual learning method for large language models with true orthogonality and reduced forgetting","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113782","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113782"}}