{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T02:02:09Z","timestamp":1780020129669,"version":"3.53.1"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"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":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.knosys.2026.116105","type":"journal-article","created":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:02:11Z","timestamp":1778889731000},"page":"116105","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Dynamic token halting for efficient abstractive summarization with importance-aware regularization"],"prefix":"10.1016","volume":"346","author":[{"given":"Heyan","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2422-0548","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minpeng","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116105_b1","doi-asserted-by":"crossref","first-page":"1449","DOI":"10.1016\/j.ipm.2007.03.009","article-title":"Automatic summarising: the state of the art","volume":"43","author":"Jones","year":"2007","journal-title":"Inf. Process. Manage."},{"key":"10.1016\/j.knosys.2026.116105_b2","doi-asserted-by":"crossref","unstructured":"A. See, P. Liu, C. Manning, Get To The Point: Summarization with Pointer-Generator Networks, in: Proceedings Of The 55th Annual Meeting Of The Association For Computational Linguistics (Volume 1: Long Papers), 2017, pp. 1073\u20131083.","DOI":"10.18653\/v1\/P17-1099"},{"key":"10.1016\/j.knosys.2026.116105_b3","doi-asserted-by":"crossref","unstructured":"N. Moratanch, S. Chitrakala, A survey on extractive text summarization, in: 2017 International Conference on Computer, Communication and Signal Processing, ICCCSP, 2017, pp. 1\u20136.","DOI":"10.1109\/ICCCSP.2017.7944061"},{"key":"10.1016\/j.knosys.2026.116105_b4","doi-asserted-by":"crossref","first-page":"5755","DOI":"10.1016\/j.eswa.2013.04.023","article-title":"Assessing sentence scoring techniques for extractive text summarization","volume":"40","author":"Ferreira","year":"2013","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.116105_b5","series-title":"Ranking sentences for extractive summarization with reinforcement learning","author":"Narayan","year":"2018"},{"key":"10.1016\/j.knosys.2026.116105_b6","series-title":"Proceedings Of The 45th Annual Meeting Of The Association For Computational Linguistics Companion Volume Proceedings Of The Demo And Poster Sessions","first-page":"185","article-title":"Extractive summarization based on event term clustering","author":"Liu","year":"2007"},{"key":"10.1016\/j.knosys.2026.116105_b7","doi-asserted-by":"crossref","unstructured":"M. Lewis, Y. Liu, N. Goyal, M. Ghazvininejad, A. Mohamed, O. Levy, V. Stoyanov, L. Zettlemoyer, BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension, in: Proceedings Of The 58th Annual Meeting Of The Association For Computational Linguistics, 2020, pp. 7871\u20137880.","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"10.1016\/j.knosys.2026.116105_b8","series-title":"International Conference On Machine Learning","first-page":"11328","article-title":"Pegasus: Pre-training with extracted gap-sentences for abstractive summarization","author":"Zhang","year":"2020"},{"key":"10.1016\/j.knosys.2026.116105_b9","doi-asserted-by":"crossref","unstructured":"Y. Liu, M. Lapata, Text Summarization with Pretrained Encoders, in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019, pp. 3730\u20133740.","DOI":"10.18653\/v1\/D19-1387"},{"key":"10.1016\/j.knosys.2026.116105_b10","series-title":"Adaptive computation time for recurrent neural networks","author":"Graves","year":"2016"},{"key":"10.1016\/j.knosys.2026.116105_b11","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.knosys.2026.116105_b12","first-page":"13933","article-title":"Exploring explainable selection to control abstractive summarization","volume":"vol. 35","author":"Wang","year":"2021"},{"key":"10.1016\/j.knosys.2026.116105_b13","series-title":"Mass: Masked sequence to sequence pre-training for language generation","author":"Song","year":"2019"},{"key":"10.1016\/j.knosys.2026.116105_b14","doi-asserted-by":"crossref","unstructured":"Y. Liu, P. Liu, SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization, in: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), 2021, pp. 1065\u20131072.","DOI":"10.18653\/v1\/2021.acl-short.135"},{"key":"10.1016\/j.knosys.2026.116105_b15","doi-asserted-by":"crossref","unstructured":"Y. Liu, P. Liu, D. Radev, G. Neubig, BRIO: Bringing Order to Abstractive Summarization, in: Proceedings Of The 60th Annual Meeting Of The Association For Computational Linguistics (Volume 1: Long Papers), 2022, pp. 2890\u20132903.","DOI":"10.18653\/v1\/2022.acl-long.207"},{"key":"10.1016\/j.knosys.2026.116105_b16","article-title":"Unified language model pre-training for natural language understanding and generation","volume":"32","author":"Dong","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116105_b17","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.knosys.2026.116105_b18","series-title":"Efficient summarization with read-again and copy mechanism","author":"Zeng","year":"2016"},{"key":"10.1016\/j.knosys.2026.116105_b19","doi-asserted-by":"crossref","unstructured":"Y. Chen, M. Bansal, Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting, in: Proceedings Of The 56th Annual Meeting Of The Association For Computational Linguistics (Volume 1: Long Papers), 2018, pp. 675\u2013686.","DOI":"10.18653\/v1\/P18-1063"},{"key":"10.1016\/j.knosys.2026.116105_b20","doi-asserted-by":"crossref","unstructured":"Y. Liu, M. Lapata, Hierarchical Transformers for Multi-Document Summarization, in: Proceedings Of The 57th Annual Meeting Of The Association For Computational Linguistics, 2019, pp. 5070\u20135081.","DOI":"10.18653\/v1\/P19-1500"},{"key":"10.1016\/j.knosys.2026.116105_b21","doi-asserted-by":"crossref","unstructured":"L. Huang, S. Cao, N. Parulian, H. Ji, L. Wang, Efficient Attentions for Long Document Summarization, in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, pp. 1419\u20131436.","DOI":"10.18653\/v1\/2021.naacl-main.112"},{"key":"10.1016\/j.knosys.2026.116105_b22","series-title":"Longt5: Efficient text-to-text transformer for long sequences","author":"Guo","year":"2021"},{"key":"10.1016\/j.knosys.2026.116105_b23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3530811","article-title":"Efficient transformers: A survey","volume":"55","author":"Tay","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.knosys.2026.116105_b24","unstructured":"N. Parmar, A. Vaswani, J. Uszkoreit, L. Kaiser, N. Shazeer, A. Ku, D. Tran, Image transformer, in: International Conference On Machine Learning, 2018, pp. 4055\u20134064."},{"key":"10.1016\/j.knosys.2026.116105_b25","series-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019"},{"key":"10.1016\/j.knosys.2026.116105_b26","series-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020"},{"key":"10.1016\/j.knosys.2026.116105_b27","series-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"10.1016\/j.knosys.2026.116105_b28","series-title":"Token pooling in vision transformers","author":"Marin","year":"2021"},{"key":"10.1016\/j.knosys.2026.116105_b29","doi-asserted-by":"crossref","unstructured":"W. Zeng, S. Jin, W. Liu, C. Qian, P. Luo, W. Ouyang, X. Wang, Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11101\u201311111.","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"10.1016\/j.knosys.2026.116105_b30","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116105_b31","series-title":"Ats: Adaptive token sampling for efficient vision transformers","author":"Fayyaz","year":"2021"},{"key":"10.1016\/j.knosys.2026.116105_b32","doi-asserted-by":"crossref","unstructured":"H. Yin, A. Vahdat, J. Alvarez, A. Mallya, J. Kautz, P. Molchanov, A-ViT: Adaptive Tokens for Efficient Vision Transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10809\u201310818.","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"10.1016\/j.knosys.2026.116105_b33","doi-asserted-by":"crossref","unstructured":"M. Li, C. Zoril\u0103, R. Doddipatla, Transformer-based online speech recognition with decoder-end adaptive computation steps, in: 2021 IEEE Spoken Language Technology Workshop, SLT, 2021, pp. 1\u20137.","DOI":"10.1109\/SLT48900.2021.9383613"},{"key":"10.1016\/j.knosys.2026.116105_b34","doi-asserted-by":"crossref","unstructured":"F. Schneider, A. Waibel, Towards stream translation: Adaptive computation time for simultaneous machine translation, in: Proceedings of the 17th International Conference on Spoken Language Translation, 2020, pp. 228\u2013236.","DOI":"10.18653\/v1\/2020.iwslt-1.28"},{"key":"10.1016\/j.knosys.2026.116105_b35","doi-asserted-by":"crossref","unstructured":"J. Lee, E. Mansimov, K. Cho, Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, pp. 1173\u20131182.","DOI":"10.18653\/v1\/D18-1149"},{"key":"10.1016\/j.knosys.2026.116105_b36","doi-asserted-by":"crossref","unstructured":"L. Qian, H. Zhou, Y. Bao, M. Wang, L. Qiu, W. Zhang, Y. Yu, L. Li, Glancing Transformer for Non-Autoregressive Neural Machine Translation, in: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 1993\u20132003, (2021, 8). https:\/\/aclanthology.org\/2021.acl-long.155.","DOI":"10.18653\/v1\/2021.acl-long.155"},{"key":"10.1016\/j.knosys.2026.116105_b37","series-title":"Non-autoregressive translation with layer-wise prediction and deep supervision","author":"Huang","year":"2021"},{"key":"10.1016\/j.knosys.2026.116105_b38","article-title":"Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time","volume":"36","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116105_b39","article-title":"H2o: Heavy-hitter oracle for efficient generative inference of large language models","volume":"36","author":"Zhang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116105_b40","series-title":"Transformers are multi-state rnns","author":"Oren","year":"2024"},{"key":"10.1016\/j.knosys.2026.116105_b41","series-title":"Model tells you what to discard: Adaptive kv cache compression for llms","author":"Ge","year":"2023"},{"key":"10.1016\/j.knosys.2026.116105_b42","unstructured":"C.R. Lin, A package for automatic evaluation of summaries, in: Text Summarization Branches Out, 2004, pp. 74\u201381."},{"key":"10.1016\/j.knosys.2026.116105_b43","article-title":"Teaching machines to read and comprehend","volume":"28","author":"Hermann","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116105_b44","doi-asserted-by":"crossref","unstructured":"S. Narayan, S. Cohen, M. Lapata, Don\u2019t Give Me the Details and Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018.","DOI":"10.18653\/v1\/D18-1206"},{"key":"10.1016\/j.knosys.2026.116105_b45","doi-asserted-by":"crossref","unstructured":"R. Dror, G. Baumer, S. Shlomov, R. Reichart, The hitchhiker\u2019s guide to testing statistical significance in natural language processing, in: Proceedings Of The 56th Annual Meeting Of The Association For Computational Linguistics (Volume 1: Long Papers), 2018, pp. 1383\u20131392.","DOI":"10.18653\/v1\/P18-1128"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008312?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008312?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:05:33Z","timestamp":1780016733000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126008312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":45,"alternative-id":["S0950705126008312"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116105","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dynamic token halting for efficient abstractive summarization with importance-aware regularization","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116105","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":"116105"}}