{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:32:04Z","timestamp":1773001924915,"version":"3.50.1"},"reference-count":36,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"vor","delay-in-days":196,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>Machine learning\u2013based classifiers have been used for text classification, such as sentiment analysis, news classification, and toxic comment classification. However, supervised machine learning models often require large amounts of labeled data for training, and manual annotation is both labor\u2010intensive and requires domain\u2010specific knowledge, leading to relatively high annotation costs. To address this issue, we propose an approach that integrates large language models (LLMs) into an active learning framework, achieving high cross\u2010task text classification performance without the need for any manually labeled data. Furthermore, compared to directly applying GPT for classification tasks, our approach retains over 93% of its classification performance while requiring only approximately 6% of the computational time and monetary cost, effectively balancing performance and resource efficiency. These findings provide new insights into the efficient utilization of LLMs and active learning algorithms in text classification tasks, paving the way for their broader application.<\/jats:p>","DOI":"10.1155\/int\/6472544","type":"journal-article","created":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T03:50:32Z","timestamp":1752724232000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Applying LLMs to Active Learning: Toward Cost\u2010Efficient Cross\u2010Task Text Classification Without Manually Labeled Data"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6824-2589","authenticated-orcid":false,"given":"Yejian","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Shingo","family":"Takada","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"e_1_2_11_1_2","doi-asserted-by":"publisher","DOI":"10.3390\/info13020083"},{"key":"e_1_2_11_2_2","unstructured":"MinaeeS. KalchbrennerN. CambriaE. NikzadN. ChenaghluM. andGaoJ. Deep Learning Based Text Classification: A Comprehensive Review 2020 https:\/\/arxiv.org\/abs\/2004.03705."},{"key":"e_1_2_11_3_2","unstructured":"SettlesB. Active Learning Literature Survey 2009 University of Wisconsin\u2013Madison Computer Sciences Technical Report 1648."},{"key":"e_1_2_11_4_2","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"e_1_2_11_5_2","doi-asserted-by":"crossref","unstructured":"TomanekK.andHahnU. Semi-Supervised Active Learning for Sequence Labeling Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP Ser. ACL \u201909 2009 Stroudsburg Association for Computational Linguistics 1039\u20131047 https:\/\/aclanthology.org\/P09-1117.","DOI":"10.3115\/1690219.1690291"},{"key":"e_1_2_11_6_2","doi-asserted-by":"crossref","unstructured":"StrubellE. GaneshA. andMcCallumA. Energy and Policy Considerations for Deep Learning in Nlp Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics 2019 Florence Italy.","DOI":"10.18653\/v1\/P19-1355"},{"key":"e_1_2_11_7_2","doi-asserted-by":"crossref","unstructured":"BenderE. M. GebruT. McMillan-MajorA. andShmitchellS. On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? Proceedings of the 2021 ACM Conference on Fairness Accountability and Transparency 2021 New York.","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_2_11_8_2","first-page":"1877","article-title":"Language Models Are Few-Shot Learners","volume":"33","author":"Brown T. B.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_9_2","first-page":"7937","article-title":"Memory-Efficient Pipeline-Parallel Dnn Training","volume":"139","author":"Narayanan D.","year":"2021","journal-title":"Proceedings of Machine Learning Research"},{"key":"e_1_2_11_10_2","unstructured":"RaeJ. W. BorgeaudS. CaiT.et al. Scaling Language Models: Methods Analysis & Insights From Training Gopher 2021 https:\/\/arxiv.org\/abs\/2112.11446."},{"key":"e_1_2_11_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3365742"},{"key":"e_1_2_11_12_2","unstructured":"MaasA. L. DalyR. E. PhamP. T. HuangD. NgA. Y. andPottsC. Learning Word Vectors for Sentiment Analysis Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies June 2011 Portland Association for Computational Linguistics 142\u2013150 http:\/\/www.aclweb.org\/anthology\/P11-1015."},{"key":"e_1_2_11_13_2","first-page":"649","article-title":"Character-Level Convolutional Networks for Text Classification","volume":"28","author":"Zhang X.","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_14_2","unstructured":"TeamJ. A. Jigsaw Toxic Comment Classification Challenge Dataset 2018 https:\/\/www.kaggle.com\/c\/jigsaw-toxic-comment-classification-challenge\/data."},{"key":"e_1_2_11_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/505282.505283"},{"key":"e_1_2_11_16_2","doi-asserted-by":"crossref","unstructured":"PangB. LeeL. andVaithyanathanS. Thumbs up?: Sentiment Classification Using Machine Learning Techniques Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing-Volume 10 2002 Stroudsburg Association for Computational Linguistics 79\u201386.","DOI":"10.3115\/1118693.1118704"},{"key":"e_1_2_11_17_2","doi-asserted-by":"crossref","unstructured":"AndroutsopoulosI. KoutsiasJ. ChandrinosV. andSpyropoulosC. D. An Experimental Comparison of Naive Bayesian and Keyword-Based Anti-Spam Filtering With Personal E-Mail Messages Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval 2000 Athens Greece ACM 160\u2013167.","DOI":"10.1145\/345508.345569"},{"key":"e_1_2_11_18_2","unstructured":"LewisD. D.andGaleW. A. A Sequential Algorithm for Training Text Classifiers Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval 1994 Dublin Ireland Springer-Verlag New York Inc 3\u201312."},{"key":"e_1_2_11_19_2","doi-asserted-by":"publisher","DOI":"10.3390\/info10040150"},{"key":"e_1_2_11_20_2","unstructured":"ZhangY.andWallaceB. C. A Sensitivity Analysis of (and Practitioners\u2019 Guide to) Convolutional Neural Networks for Sentence Classification 2015 https:\/\/arxiv.org\/abs\/1510.03820."},{"key":"e_1_2_11_21_2","unstructured":"DevlinJ. ChangM.-W. LeeK. andToutanovaK. Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding 2018 https:\/\/arxiv.org\/abs\/1810.04805."},{"key":"e_1_2_11_22_2","unstructured":"LiuY. OttM. GoyalN.et al. Roberta: A Robustly Optimized Bert Pretraining Approach 2019 https:\/\/arxiv.org\/abs\/1907.11692."},{"key":"e_1_2_11_23_2","unstructured":"OpenAI Gpt-4 Technical Report 2023 https:\/\/arxiv.org\/abs\/2303.08774."},{"key":"e_1_2_11_24_2","unstructured":"OpenAI Gpt-4o System Card 2024 https:\/\/arxiv.org\/abs\/2410.21276."},{"key":"e_1_2_11_25_2","doi-asserted-by":"crossref","unstructured":"IzacardG.andGraveE. MerloP. TiedemannJ. andTsarfatyR. Leveraging Passage Retrieval With Generative Models for Open Domain Question Answering Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume April 2021 Association for Computational Linguistics 874\u2013880 https:\/\/aclanthology.org\/2021.eacl-main.74\/.","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"e_1_2_11_26_2","unstructured":"GoyalT. LiJ. J. andDurrettG. News Summarization and Evaluation in the Era of Gpt-3 2022 https:\/\/arxiv.org\/abs\/2209.12356."},{"key":"e_1_2_11_27_2","unstructured":"ChenM. TworekJ. JunH.et al. Evaluating Large Language Models Trained on Code 2021 https:\/\/arxiv.org\/abs\/2107.03374."},{"key":"e_1_2_11_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/bf00116828"},{"key":"e_1_2_11_29_2","doi-asserted-by":"crossref","unstructured":"SeungH. S. OpperM. andSompolinskyH. Query by Committee Proceedings of the Fifth Annual Workshop on Computational Learning Theory Ser. COLT \u201992 1992 New York Association for Computing Machinery 287\u2013294 https:\/\/doi.org\/10.1145\/130385.130417.","DOI":"10.1145\/130385.130417"},{"key":"e_1_2_11_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/bf00993277"},{"key":"e_1_2_11_31_2","unstructured":"BrinkerK. Incorporating Diversity in Active Learning With Support Vector Machines Proceedings of the Twentieth International Conference on International Conference on Machine Learning Ser. ICML\u201903 2003 Washington AAAI Press 59\u201366."},{"key":"e_1_2_11_32_2","unstructured":"SenerO.andSavareseS. Active Learning for Convolutional Neural Networks: A Core-Set Approach International Conference on Learning Representations 2018 Vancouver Canada https:\/\/openreview.net\/forum?id=H1aIuk-RW."},{"key":"e_1_2_11_33_2","doi-asserted-by":"crossref","unstructured":"SettlesB.andCravenM. LapataM.andNgH. T. An Analysis of Active Learning Strategies for Sequence Labeling Tasks Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing October 2008 Honolulu Association for Computational Linguistics 1070\u20131079 https:\/\/aclanthology.org\/D08-1112\/.","DOI":"10.3115\/1613715.1613855"},{"key":"e_1_2_11_34_2","first-page":"45","article-title":"Support Vector Machine Active Learning With Applications to Text Classification","volume":"2001","author":"Tong S.","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_11_35_2","doi-asserted-by":"crossref","unstructured":"JoshiA. J. PorikliF. andPapanikolopoulosN. Multi-Class Active Learning for Image Classification 2009 IEEE Conference on Computer Vision and Pattern Recognition 2009 Miami 2372\u20132379.","DOI":"10.1109\/CVPR.2009.5206627"},{"key":"e_1_2_11_36_2","doi-asserted-by":"crossref","unstructured":"ZhangY.andTakadaS. Applying Llms to Active Learning: Towards Cost-Efficient Cross-Task Text Classification Without Manually Labeled Data 2025 https:\/\/arxiv.org\/abs\/2502.16892.","DOI":"10.1155\/int\/6472544"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/6472544","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/6472544","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/6472544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:05:46Z","timestamp":1772993146000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/6472544"}},"subtitle":[],"editor":[{"given":"Lijie","family":"Wen","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/6472544"],"URL":"https:\/\/doi.org\/10.1155\/int\/6472544","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-05-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-23","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"6472544"}}