{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:55:13Z","timestamp":1774965313463,"version":"3.50.1"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T00:00:00Z","timestamp":1747094400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T00:00:00Z","timestamp":1747094400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s10115-025-02450-1","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:13:09Z","timestamp":1747156389000},"page":"7431-7450","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Dynamic token pruning for LLMs: leveraging task-specific attention and adaptive thresholds"],"prefix":"10.1007","volume":"67","author":[{"given":"Seyed Hossein","family":"Ahmadpanah","sequence":"first","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Sanaz","family":"Sobhanloo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Pania","family":"Afsharfarnia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,13]]},"reference":[{"key":"2450_CR1","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30"},{"key":"2450_CR2","unstructured":"Han S, Mao H, Dally WJ (2015) Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149"},{"key":"2450_CR3","unstructured":"Chen T, Zhou Y, Chen Y, Sun L, Xu J, Qian X (2020) Efficient inference on large language models via dynamic tree pruning. arXiv preprint arXiv:2007.14423"},{"key":"2450_CR4","doi-asserted-by":"crossref","unstructured":"Keith C, Robinson M, Duncan F, Worthington A, Wilson J, Harris S (2024) Optimizing large language models: A novel approach through dynamic token pruning. Research Square","DOI":"10.21203\/rs.3.rs-5293588\/v1"},{"key":"2450_CR5","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I (2019) Language models are unsupervised multitask learners. OpenAI Blog 1(8)"},{"key":"2450_CR6","unstructured":"Li H, Kadambi S, Nocedal J, Kumar A (2016) Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710"},{"key":"2450_CR7","unstructured":"Guo Y, Yao A, Chen Y (2016) Dynamic network surgery for efficient deep neural networks. In: Advances in Neural Information Processing Systems, vol. 29"},{"key":"2450_CR8","doi-asserted-by":"crossref","unstructured":"Jacob B, Kligys S, Zemel R, Brahma D (2018) Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2018.00286"},{"key":"2450_CR9","unstructured":"Bhalgat S, Raghunathan A, Narayanan VK (2020) Training quantized neural networks using full precision gradients. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"2450_CR10","unstructured":"Micikevicius P, Narayanan S, Raina R (2017) Mixed precision training. In: International Conference on Learning Representations"},{"key":"2450_CR11","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531"},{"key":"2450_CR12","doi-asserted-by":"crossref","unstructured":"Jiao X, Yin Y, Shang L, Jiang X, Chen X, Li L, Zhou J (2019) Tinybert: Distilling transformer for language understanding. arXiv preprint arXiv:1909.10351","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"2450_CR13","doi-asserted-by":"crossref","unstructured":"Howard J, Ruder S (2018) Universal language model fine-tuning for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 328\u2013339","DOI":"10.18653\/v1\/P18-1031"},{"key":"2450_CR14","doi-asserted-by":"crossref","unstructured":"Gururangan S, Marasovi\u0107 A, Swayamdipta S, Lo K, Beltagy I, Kocisky T (2020) Don\u2019t stop pretraining: Adapt language models to domains and tasks. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"2450_CR15","doi-asserted-by":"crossref","unstructured":"Jin W, Gao Y, Tao T, Wang X, Wang N, Wu B, Zhao B (2025) Veracity-oriented context-aware large language models-based prompting optimization for fake news detection. Int. J. Intell. Syst. 2025","DOI":"10.1155\/int\/5920142"},{"key":"2450_CR16","doi-asserted-by":"crossref","unstructured":"Zhang W, Li X, Deng Y, Bing L, Lam W (2021) Towards generative aspect-based sentiment analysis. Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.acl-short.64"},{"issue":"6","key":"2450_CR17","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1109\/TCSS.2020.3033302","volume":"7","author":"H Liu","year":"2020","unstructured":"Liu H, Chatterjee I, Zhou M, Lu XS, Abusorrah A (2020) Aspect-based sentiment analysis: a survey of deep learning methods. IEEE Trans Comput Soc Syst 7(6):1358\u20131375","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"2450_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122289","volume":"238","author":"W Jin","year":"2024","unstructured":"Jin W, Zhao B, Zhang Y, Huang J, Yu H (2024) Wordtransabsa: enhancing aspect-based sentiment analysis with masked language modeling for affective token prediction. Expert Syst Appl 238:122289. https:\/\/doi.org\/10.1016\/j.eswa.2023.122289","journal-title":"Expert Syst Appl"},{"key":"2450_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126708","volume":"557","author":"B Zhao","year":"2023","unstructured":"Zhao B, Jin W, Del Ser J, Yang G (2023) Chatagri: exploring potentials of chatgpt on cross-linguistic agricultural text classification. Neurocomputing 557:126708. https:\/\/doi.org\/10.1016\/j.neucom.2023.126708","journal-title":"Neurocomputing"},{"key":"2450_CR20","doi-asserted-by":"crossref","unstructured":"Jiang M, Liu G, Su Y, Jin W, Zhao B (2025) Hierarchical multi-relational graph representation learning for large-scale prediction of drug-drug interactions. IEEE Transactions on Big Data","DOI":"10.1109\/TBDATA.2025.3536924"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-025-02450-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-025-02450-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-025-02450-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T14:48:48Z","timestamp":1757170128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-025-02450-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,13]]},"references-count":20,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["2450"],"URL":"https:\/\/doi.org\/10.1007\/s10115-025-02450-1","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,13]]},"assertion":[{"value":"10 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose. The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}