{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T06:29:50Z","timestamp":1763101790941,"version":"3.45.0"},"reference-count":31,"publisher":"Tech Science Press","issue":"3","license":[{"start":{"date-parts":[[2025,3,16]],"date-time":"2025-03-16T00:00:00Z","timestamp":1742083200000},"content-version":"vor","delay-in-days":74,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.057443","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T02:34:43Z","timestamp":1737513283000},"page":"4003-4019","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["AdaptForever: Elastic and Mutual Learning for Continuous NLP Task Mastery"],"prefix":"10.32604","volume":"82","author":[{"given":"Ke","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyang","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiakang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref2","series-title":"Proceedings of the 20th Chinese National Conference on Computational Linguistics","first-page":"1218","article-title":"A robustly optimized BERT pre-training approach with post-training","author":"Zhuang","year":"2021"},{"key":"ref3","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"3645","article-title":"Energy and policy considerations for deep learning in NLP","author":"Strubell","year":"2019"},{"key":"ref4","series-title":"Paper presented at: Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref5","unstructured":"He J, Zhou C, Ma X, Berg-Kirkpatrick T, Neubig G. Towards a unified view of parameter-efficient transfer learning. arXiv:2110.04366. 2021."},{"key":"ref6","unstructured":"Houlsby N, Giurgiu A, Jastrzebski S, Morrone B, de Laroussilhe Q, Gesmundo A, et al. Parameter-efficient transfer learning for NLP. arXiv:1902.00751. 2019."},{"key":"ref7","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, et al. Lora: low-rank adaptation of large language models. arXiv:2106.09685. 2021."},{"key":"ref8","series-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics","first-page":"487","article-title":"AdapterFusion: non-destructive task composition for transfer learning","author":"Pfeiffer","year":"2021"},{"key":"ref9","series-title":"Paper presented at: Proceedings of the 36th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","article-title":"BERT and PALs: projected attention layers for efficient adaptation in multi-task learning","author":"Stickland","year":"2019."},{"key":"ref10","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"5744","article-title":"AdaMix: mixture-of-adaptations for parameter-efficient model tuning","author":"Wang","year":"2022"},{"key":"ref11","series-title":"International Conference on Learning Representations","article-title":"Adaptive budget allocation for parameter-efficient fine-tuning","author":"Zhang","year":"2023"},{"key":"ref12","unstructured":"Zuo S, Liu X, Jiao J, Kim YJ, Hassan H, Zhang R, et al. Taming sparsely activated transformer with stochastic experts. arXiv:2110.04260. 2021."},{"key":"ref13","series-title":"International Conference on Learning Representations","article-title":"Outrageously large neural networks: the sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2016"},{"key":"ref14","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4320","article-title":"Deep mutual learning","author":"Zhang","year":"2018"},{"key":"ref15","series-title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI-22)","first-page":"4164","article-title":"MuiDial: improving dialogue disentanglement with intent-based mutual learning","author":"Jiang","year":"2022"},{"key":"ref16","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 Nat Acad Sci"},{"key":"ref17","series-title":"NIPS.17: Proceedings of the 31st International Conference on Neural Information Processing Systems","first-page":"6000","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"120","article-title":"Switch transformers: scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J Mach Learn Res"},{"key":"ref19","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"7930","article-title":"AdapterDrop: on the efficiency of adapters in transformers","author":"R\u00fcckl\u00e9","year":"2021"},{"key":"ref20","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","first-page":"2208","article-title":"On the effectiveness of adapter-based tuning for pretrained language model adaptation","author":"He","year":"2021"},{"key":"ref21","unstructured":"Li D, Ma Y, Wang N, Ye Z, Cheng Z, Tang Y, et al. MixLoRA: enhancing large language models fine-tuning with lora based mixture of experts. arXiv:2404.15159. 2024."},{"key":"ref22","unstructured":"Schulhoff S, Ilie M, Balepur N, Kahadze K, Liu A, Si C, et al. The prompt report: a systematic survey of prompting techniques. arXiv:2406.06608. 2024."},{"key":"ref23","unstructured":"Kepel D, Valogianni K. Autonomous prompt engineering in large language models. arXiv:2407.11000. 2024."},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"Li Y, Luo F, Tan C, Wang M, Huang S, Li S, et al. Parameter-efficient sparsity for large language models fine-tuning. arXiv:2205.11005. 2022.","DOI":"10.24963\/ijcai.2022\/586"},{"key":"ref25","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","first-page":"1","article-title":"BitFit: simple parameter-efficient fine-tuning for transformer-based masked language-models","author":"Ben Zake","year":"2022"},{"key":"ref26","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"8440","article-title":"Unsupervised cross-lingual representation learning at scale","author":"Conneau","year":"2020"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"102631","DOI":"10.1016\/j.ipm.2021.102631","article-title":"Misinformation detection using multitask learning with mutual learning for novelty detection and emotion recognition","volume":"58","author":"Kumari","year":"2021","journal-title":"Inf Process Manage"},{"key":"ref28","unstructured":"Lepikhin D, Lee H, Xu Y, Chen D, Firat O, Huang Y, et al. GShard: scaling giant models with conditional computation and automatic sharding. arXiv:2006.16668. 2020."},{"key":"ref29","doi-asserted-by":"crossref","first-page":"E2496\u20137","DOI":"10.1073\/pnas.1717042115","article-title":"Note on the quadratic penalties in elastic weight consolidation","volume":"115","author":"Husz\u00e1r","year":"2018","journal-title":"Proc National Acad Sci"},{"key":"ref30","unstructured":"Batra H, Clark R. EVCL: elastic variational continual learning with weight consolidation. arXiv:2406.15972. 2024."},{"key":"ref31","series-title":"Proceedings of the 28th International Conference on Computational Linguistics","first-page":"6523","article-title":"Continual lifelong learning in natural language processing: a survey","author":"Biesialska","year":"2020"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-82-3\/TSP_CMC_57443\/TSP_CMC_57443.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T06:28:20Z","timestamp":1763101700000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v82n3\/59874"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":31,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.057443","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2024-08-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-10","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-06","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}