{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:17:47Z","timestamp":1777706267920,"version":"3.51.4"},"reference-count":43,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"Fujian province middle-aged youth fund","award":["JAT220572"],"award-info":[{"award-number":["JAT220572"]}]},{"name":"school fund","award":["YZDKJ23-04"],"award-info":[{"award-number":["YZDKJ23-04"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:p>Large Language Models (LLMs) have demonstrated impressive capabilities in text summarization and question answering. However, their outputs often rely on shallow rephrasing of the input, leading to summaries that may overlook key information or misrepresent the source content. Moreover, LLMs face challenges when processing excessively long inputs due to context limitations and information dilution. To address these issues, we propose a two-stage text compression framework based on lightweight LLMs. In the first stage, semantically salient text units are identified using a combination of lightweight LLM scoring and embedding-based ranking to achieve concise input compression. In the second stage, the same lightweight LLM is employed to regenerate coherent and informative summaries from the compressed inputs. Experimental results on multiple QA datasets demonstrate that our system achieves competitive performance against standard baselines while significantly reducing model size and input length. The framework is highly adaptable, interpretable, and suitable for integration into resource-constrained environments and document processing scenarios characterized by noisy or semantically irrelevant content.<\/jats:p>","DOI":"10.1177\/18758967251375117","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T15:31:01Z","timestamp":1757691061000},"page":"1307-1318","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Text Compression Algorithm Based on Feedback Self-Optimization Using Lightweight LLMs"],"prefix":"10.1177","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8366-4356","authenticated-orcid":false,"given":"Ziyue","family":"Wang","sequence":"first","affiliation":[{"name":"Universiti Sains Malaysia"},{"name":"Fujian Polytechnic of Information Technology, FuZhou, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5569-2495","authenticated-orcid":false,"given":"Chia Yean","family":"Lim","sequence":"additional","affiliation":[{"name":"Universiti Sains Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1058-4595","authenticated-orcid":false,"given":"Xingshuai","family":"Jia","sequence":"additional","affiliation":[{"name":"Universiti Sains Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14020713"},{"issue":"8","key":"e_1_3_3_3_1","first-page":"1762","article-title":"Multi-document news web page summarization using content extraction and lexical chain based key phrase extraction","volume":"13","author":"Arya C.","year":"2023","unstructured":"Arya C., Diwakar M., Singh P., Kadry S., , &\u00a0Kim, J. (2023). Multi-document news web page summarization using content extraction and lexical chain based key phrase extraction. Applied Sciences, 13(8), 1762. https:\/\/doi.org\/10.3390\/math11081762","journal-title":"Applied Sciences"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2685317"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4021"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.89"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.845"},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.16"},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-017-1349-x"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05747-w"},{"issue":"6","key":"e_1_3_3_11_1","first-page":"24","article-title":"OBOE: an explainable text classi-fication framework","volume":"8","author":"del \u00c1guila Escobar R. A.","year":"2024","unstructured":"del \u00c1guila Escobar R. A., Su\u00e1rez-Figueroa M. C., Fern\u00e1ndez-L\u00f3pez M. (2024). OBOE: an explainable text classi-fication framework. International Journal of Interactive Multimedia and Artificial Intel-Ligence, 8(6), 24\u201337. https:\/\/doi.org\/10.9781\/ijimai.2022.11.001","journal-title":"International Journal of Interactive Multimedia and Artificial Intel-Ligence"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.websem.2011.04.004"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.345"},{"key":"e_1_3_3_14_1","article-title":"Unified extractive-abstractive summarization: A hybrid approach utilizing BERT and transformer models for enhanced document summarization","volume":"10","author":"Divya S.","year":"2024","unstructured":"Divya S., Sripriya N., Andrew J., , &\u00a0Mazzara, M. (2024). Unified extractive-abstractive summarization: A hybrid approach utilizing BERT and transformer models for enhanced document summarization. Peer-reviewed Open Access journal, 10, e2424. https:\/\/doi.org\/10.7717\/peerj-cs.2424","journal-title":"Peer-reviewed Open Access journal"},{"key":"e_1_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-80599-9_8"},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/35.3.243"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04607-3"},{"key":"e_1_3_3_18_1","doi-asserted-by":"crossref","unstructured":"Garg S. Tsipras D. Liang P. S. &\u00a0Valiant G. (2022). What can transformers learn in-context? A case study of simple function classes.Advances in Neural Information Processing Systems 35 30583\u201330598.","DOI":"10.52202\/068431-2217"},{"key":"e_1_3_3_19_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/JBHI.2025.3558935","article-title":"Adaptive Compressed-based Privacy-preserving Large Language Model for Sensitive Healthcare","author":"Gong X.","year":"2025","unstructured":"Gong X., Gao J., Sun S., Zhong Z., Shi Y., , &\u00a0Zeng, H. (2025). Adaptive Compressed-based Privacy-preserving Large Language Model for Sensitive Healthcare. IEEE Journal of Biomedical and Health Informatics, 1\u201313. https:\/\/doi.org\/10.1109\/JBHI.2025.3558935","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14199103"},{"key":"e_1_3_3_21_1","unstructured":"Han Y. Liu C. Wang P. (2023). A comprehensive survey on vector database: storage and retrieval technique challenge. arXiv preprint. arXiv:2310.11703."},{"key":"e_1_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"e_1_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.91"},{"issue":"4","key":"e_1_3_3_24_1","first-page":"535","article-title":"Billion-scale similarity search with GPUs","volume":"5","author":"Johnson J.","year":"2019","unstructured":"Johnson J., Douze M., J\u00e9gou H. (2019). Billion-scale similarity search with GPUs. IEEE Trans Big Data, 5(4), 535\u2013547. https:\/\/doi.org\/10.1109\/TBDATA.2019.2921572","journal-title":"IEEE Trans Big Data"},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_3_27_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 (NeurIPS 2020) (pp. 1\u201312)","author":"Lewis P.","year":"2020","unstructured":"Lewis P., Perez E., Piktus A., Petroni F., Karpukhin V., Goyal N., K\u00fcttler H., Lewis M., Yih W. T., Rockt\u00e4schel T., Riedel S., , &\u00a0Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks.Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 (NeurIPS 2020) (pp. 1\u201312)."},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113471"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.391"},{"key":"e_1_3_3_30_1","first-page":"74","volume-title":"Text summarization branches out","author":"Lin C. Y.","year":"2004","unstructured":"Lin C. Y. (2004). ROUGE: A package for automatic evaluation of summaries. In Text summarization branches out (pp. 74\u201381). Association for Computational Linguistics."},{"key":"e_1_3_3_31_1","unstructured":"Liu Z. Zhao C. Fedorov I. Soran B. Choudhary D. Krishnamoorthi R. Chandra V. Tian Y. &\u00a0Blankevoort T. (2024). SpinQuant\u2014LLM quantization with learned rotations. arXiv preprint. arXiv:2405.16406."},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.fss.2024.109117"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2423"},{"key":"e_1_3_3_34_1","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (pp. 311\u2013318)","author":"Papineni K.","year":"2002","unstructured":"Papineni K., Roukos S., Ward T., , &\u00a0Zhu W. J. (2002). BLEU: A method for automatic evaluation of machine translation.Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (pp. 311\u2013318)."},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/math11030611"},{"key":"e_1_3_3_36_1","first-page":"3982","volume-title":"Sentence-BERT: Sentence embeddings using siamese BERT-networks","author":"Reimers N.","year":"2019","unstructured":"Reimers N., Gurevych I. (2019). Sentence-BERT: Sentence embeddings using siamese BERT-networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (pp. 3982\u20133992), Hong Kong, China, Association for Computational Linguistics."},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70546-5_15"},{"key":"e_1_3_3_38_1","unstructured":"Touvron H. Martin L. Stone K. Albert P. Almahairi A. Babaei Y. Bashlykov N. Batra S. Bhargava P. Bhosale S. Bikel D. Blecher L. Ferrer C.C. Chen M. Cucurull G. Esiobu D. Fernandes J. Fu J. Fu W. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv preprint. arXiv:2307.09288."},{"key":"e_1_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.64"},{"key":"e_1_3_3_40_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei J.","year":"2022","unstructured":"Wei J., Wang X., Schuurmans D., Bosma M., Ichter B., Xia F., Chi E. H., Le Q. V., , &\u00a0Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824\u201324837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.365"},{"key":"e_1_3_3_42_1","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations (pp. 72\u201377)","author":"Yang W.","year":"2019","unstructured":"Yang W., Xie Y., Lin A., Li X., Tan L., Xiong K., Li M., , &\u00a0Lin, J. (2019). End-to-end open-domain question answering with bertserini.Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations (pp. 72\u201377)."},{"key":"e_1_3_3_43_1","volume-title":"8th International Conference on Learning Representations (ICLR 2020)","author":"Zhang T.","year":"2020","unstructured":"Zhang T., Kishore V., Wu F., Weinberger K. Q., , &\u00a0Artzi, Y. (2020). BERTScore: evaluating text generation with BERT. In\u00a08th International Conference on Learning Representations (ICLR 2020)."},{"key":"e_1_3_3_44_1","unstructured":"Zhao J. Ji Z. Qi P. Niu S. Tang B. &\u00a0Xiong F. (2024). Meta-chunking: Learning efficient text segmentation via logical perception. arXiv preprint. arXiv:2410.12788."}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18758967251375117","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/18758967251375117","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18758967251375117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:46:27Z","timestamp":1777455987000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/18758967251375117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1177\/18758967251375117"],"URL":"https:\/\/doi.org\/10.1177\/18758967251375117","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,12]]}}}