{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T02:01:55Z","timestamp":1780020115556,"version":"3.53.1"},"reference-count":46,"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\/501100004608","name":"Jiangsu Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"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.2026.116229","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:39:11Z","timestamp":1778812751000},"page":"116229","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Prompt based active learning with ensemble sampling strategy for small data learning in the scientific text classification scenarios"],"prefix":"10.1016","volume":"346","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3521-4178","authenticated-orcid":false,"given":"Hu","family":"Kai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhang","family":"Yaoting","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116229_bib0001","unstructured":"Q. Li et al., \"A survey on text classification: from shallow to deep learning,\" arXiv preprint arXiv:2008.00364, 2020."},{"key":"10.1016\/j.knosys.2026.116229_bib0002","first-page":"3961","article-title":"A review of AI-driven automation technologies: latest taxonomies, existing challenges, and future prospects","volume":"84","author":"Jin","year":"2025","journal-title":"Comput. Mater. Contin."},{"issue":"1","key":"10.1016\/j.knosys.2026.116229_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2023.103531","article-title":"Robust scientific text classification using prompt tuning based on data augmentation with L2 regularization","volume":"61","author":"Shi","year":"2024","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.knosys.2026.116229_bib0004","doi-asserted-by":"crossref","unstructured":"T. Schick and H. Sch\u00fctze, \"Exploiting cloze questions for few shot text classification and natural language inference,\" arXiv preprint arXiv:2001.07676, 2020.","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"10.1016\/j.knosys.2026.116229_bib0005","unstructured":"B. Settles, \"Active learning literature survey,\" 2009."},{"key":"10.1016\/j.knosys.2026.116229_bib0006","series-title":"Proceedings of the Chinese Computational Linguistics: 18th China National Conference, CCL 2019","first-page":"194","article-title":"How to fine-tune Bert for text classification?","author":"Sun","year":"2019"},{"key":"10.1016\/j.knosys.2026.116229_bib0007","unstructured":"A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever, \"Improving language understanding by generative pre-training,\" 2018."},{"key":"10.1016\/j.knosys.2026.116229_bib0008","article-title":"Xlnet: generalized autoregressive pretraining for language understanding","volume":"32","author":"Yang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116229_bib0009","doi-asserted-by":"crossref","unstructured":"J. Howard and S. Ruder, \"Universal language model fine-tuning for text classification,\" arXiv preprint arXiv:1801.06146, 2018.","DOI":"10.18653\/v1\/P18-1031"},{"key":"10.1016\/j.knosys.2026.116229_bib0010","doi-asserted-by":"crossref","unstructured":"I. Beltagy, K. Lo, and A. Cohan, \"SciBERT: a pretrained language model for scientific text,\" arXiv preprint arXiv:1903.10676, 2019.","DOI":"10.18653\/v1\/D19-1371"},{"key":"10.1016\/j.knosys.2026.116229_bib0011","doi-asserted-by":"crossref","unstructured":"X. Sun et al., \"Text classification via large language models,\" arXiv preprint arXiv:2305.08377, 2023.","DOI":"10.18653\/v1\/2023.findings-emnlp.603"},{"key":"10.1016\/j.knosys.2026.116229_bib0012","unstructured":"J.E. Hu et al., \"LoRA: low-rank adaptation of large language models,\" ArXiv, vol. abs\/2106.09685, 2021."},{"key":"10.1016\/j.knosys.2026.116229_bib0013","unstructured":"Z. Han, C. Gao, J. Liu, J. Zhang, and S.Q. Zhang, \"Parameter-efficient fine-tuning for large models: a comprehensive survey,\" p. arXiv:2403.14608Accessed on: March 01, 2024. doi: 10.48550\/arXiv.2403.14608 Available: https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240314608H."},{"key":"10.1016\/j.knosys.2026.116229_bib0014","unstructured":"H. Wu et al., \"Quartet logic: a four-step reasoning (qlfr) framework for advancing short text classification,\" arXiv preprint arXiv:2401.03158, 2024."},{"key":"10.1016\/j.knosys.2026.116229_bib0015","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"13309","article-title":"Promptboosting: black-box text classification with ten forward passes","author":"Hou","year":"2023"},{"key":"10.1016\/j.knosys.2026.116229_bib0016","unstructured":"Y. Zhang et al., \"Pushing the limit of LLM capacity for text classification,\" p. arXiv:2402.07470Accessed on: February 01, 2024. doi: 10.48550\/arXiv.2402.07470 Available: https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240207470Z."},{"issue":"5","key":"10.1016\/j.knosys.2026.116229_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.103029","article-title":"Fake news detection via knowledgeable prompt learning","volume":"59","author":"Jiang","year":"2022","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.knosys.2026.116229_bib0018","unstructured":"T. Gao, A. Fisch, and D. Chen, \"Making pre-trained language models better few-shot learners,\" arXiv preprint arXiv:2012.15723, 2020."},{"key":"10.1016\/j.knosys.2026.116229_bib0019","unstructured":"A. Grattafiori et al., \"The llama 3 herd of models,\" arXiv preprint arXiv:2407.21783, 2024."},{"key":"10.1016\/j.knosys.2026.116229_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110928","article-title":"Prompt learning for metonymy resolution: enhancing performance with internal prior knowledge of pre-trained language models","volume":"279","author":"Zhao","year":"2023","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.116229_bib0021","article-title":"A veracity dissemination consistency-based few-shot fake news detection framework by synergizing adversarial and contrastive self-supervised learning","volume":"14","author":"Jin","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.knosys.2026.116229_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110122","article-title":"A prompting multi-task learning-based veracity dissemination consistency reasoning augmentation for few-shot fake news detection","volume":"144","author":"Jin","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116229_bib0023","first-page":"13","article-title":"A sequential algorithm for training text classifiers: corrigendum and additional data","volume":"29","author":"Lewis","year":"1995"},{"issue":"11","key":"10.1016\/j.knosys.2026.116229_bib0024","doi-asserted-by":"crossref","first-page":"2159","DOI":"10.1109\/TKDE.2019.2913859","article-title":"Entropy-based sampling approaches for multi-class imbalanced problems","volume":"32","author":"Li","year":"2019","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.116229_bib0025","series-title":"Proceedings of the 18th Linguistic Annotation Workshop (LAW-XVIII)","first-page":"98","article-title":"Enhancing text classification through LLM-driven active learning and Human annotation","author":"Rouzegar","year":"2024"},{"key":"10.1016\/j.knosys.2026.116229_bib0026","series-title":"Proceedings of the 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","first-page":"1","article-title":"After: active learning based fine-tuning framework for speech emotion recognition","author":"Li","year":"2023"},{"key":"10.1016\/j.knosys.2026.116229_bib0027","first-page":"14552","volume":"1","author":"Xia","year":"2025","journal-title":"From selection to generation: a survey of llm-based active learning"},{"key":"10.1016\/j.knosys.2026.116229_bib0028","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/TACL.a.63","article-title":"ActiveLLM: large language model-based active learning for textual few-shot scenarios","volume":"14","author":"Bayer","year":"2026","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"10.1016\/j.knosys.2026.116229_bib0029","series-title":"Findings of the Association for Computational Linguistics","first-page":"4373","article-title":"Language model-driven data pruning enables efficient active learning","volume":"2026","author":"Hameed Azeemi","year":"2026"},{"key":"10.1016\/j.knosys.2026.116229_bib0030","first-page":"5011","article-title":"Active learning principles for In-context learning with large language models, Findings of the Association for Computational Linguistics","volume":"2023","author":"Margatina","year":"2023","journal-title":"EMNLP"},{"key":"10.1016\/j.knosys.2026.116229_bib0031","unstructured":"S. Mukherjee, A. Lalitha, A. Deshmukh, G. Liu, Y. Ma, and B. Kveton, \"Experimental design for active transductive inference in large language models,\" p. arXiv:2404.08846 Accessed on: April 01, 2024. doi: 10.48550\/arXiv.2404.08846 Available: https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240408846M."},{"key":"10.1016\/j.knosys.2026.116229_bib0032","first-page":"1","volume":"2024","author":"Qian","year":"2024","journal-title":"APE: active learning-based tooling for finding informative few-shot examples for LLM-based entity matching"},{"key":"10.1016\/j.knosys.2026.116229_bib0033","unstructured":"S. Mukherjee, A. Lalitha, S. Sengupta, A. Deshmukh, and B. Kveton, \"Multi-objective alignment of large language models through hypervolume maximization,\" p. arXiv:2412.05469 Accessed on: December 01, 2024. doi: 10.48550\/arXiv.2412.05469 Available: https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv241205469M."},{"key":"10.1016\/j.knosys.2026.116229_bib0034","doi-asserted-by":"crossref","unstructured":"Y. Yu, R. Zhang, R. Xu, J. Zhang, J. Shen, and C. Zhang, \"Cold-start data selection for few-shot language model fine-tuning: a prompt-based uncertainty propagation approach,\" Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023: 2499-2521.","DOI":"10.18653\/v1\/2023.acl-long.141"},{"key":"10.1016\/j.knosys.2026.116229_bib0035","unstructured":"M. Silberman, \"Active learning,\" Boston: Trustco, 1996."},{"key":"10.1016\/j.knosys.2026.116229_bib0036","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1162\/tacl_a_00028","article-title":"Measuring the evolution of a scientific field through citation frames","volume":"6","author":"Jurgens","year":"2018","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.knosys.2026.116229_bib0037","doi-asserted-by":"crossref","unstructured":"A. Cohan, W. Ammar, M. Van Zuylen, F. Cady, Structural scaffolds for citation intent classification in scientific publications, Proceedings of the 2019 conference of the North American chapter of the Association for Computational Linguistics: human language technologies, 1 (long and short papers) (2019) 3586-3596.","DOI":"10.18653\/v1\/N19-1361"},{"key":"10.1016\/j.knosys.2026.116229_bib0038","series-title":"Proceedings of the 2023 ACM\/IEEE Joint Conference on Digital Libraries (JCDL)","first-page":"51","article-title":"CitePrompt: using prompts to identify citation intent in scientific papers","author":"Lahiri","year":"2023"},{"key":"10.1016\/j.knosys.2026.116229_bib0039","unstructured":"Y. Liu et al., \"Roberta: a robustly optimized bert pretraining approach,\" arXiv preprint arXiv:1907.11692, 2019."},{"key":"10.1016\/j.knosys.2026.116229_bib0040","unstructured":"J. Devlin, M.W. Chang, K. Lee, and K. Toutanova, \"Bert: pre-training of deep bidirectional transformers for language understanding,\" arXiv preprint arXiv:1810.04805, 2018."},{"key":"10.1016\/j.knosys.2026.116229_bib0041","series-title":"Proceedings of the IFIP International Conference on Artificial Intelligence in Theory and Practice","first-page":"169","article-title":"Comparison of SVM and some older classification algorithms in text classification tasks","author":"Colas","year":"2006"},{"issue":"4","key":"10.1016\/j.knosys.2026.116229_bib0042","doi-asserted-by":"crossref","first-page":"723","DOI":"10.29207\/resti.v4i4.2156","article-title":"Emotion classification of song lyrics using bidirectional LSTM method with glove word representation weighting","volume":"4","author":"Abdillah","year":"2020","journal-title":"J. RESTI (Rekayasa Sist. Dan Teknol. Inf.)"},{"key":"10.1016\/j.knosys.2026.116229_bib0043","series-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"1480","article-title":"Hierarchical attention networks for document classification","author":"Yang","year":"2016"},{"key":"10.1016\/j.knosys.2026.116229_bib0044","doi-asserted-by":"crossref","unstructured":"P. Koloveas, S. Chatzopoulos, T. Vergoulis, C. Tryfonopoulos, Can LLMs predict citation intent? An experimental analysis of In-context learning and fine-tuning on open LLMs, International Conference on Theory and Practice of Digital Libraries, 2025, Cham: Springer Nature Switzerland, 207-224.","DOI":"10.1007\/978-3-032-05409-8_13"},{"issue":"8081","key":"10.1016\/j.knosys.2026.116229_bib0045","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.knosys.2026.116229_bib0046","unstructured":"W. Xiong et al., \"A minimalist approach to LLM reasoning: from rejection sampling to reinforce,\" p. arXiv:2504.11343 Accessed on: April 01, 2025. doi: 10.48550\/arXiv.2504.11343 Available: https:\/\/ui.adsabs.harvard.edu\/abs\/2025arXiv250411343X."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512600955X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512600955X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:05:24Z","timestamp":1780016724000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095070512600955X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":46,"alternative-id":["S095070512600955X"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116229","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":"Prompt based active learning with ensemble sampling strategy for small data learning in the scientific text classification scenarios","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116229","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":"116229"}}