{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T19:42:55Z","timestamp":1780342975676,"version":"3.54.1"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010712","name":"Vietnam National University","doi-asserted-by":"publisher","award":["QG.24.37"],"award-info":[{"award-number":["QG.24.37"]}],"id":[{"id":"10.13039\/501100010712","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015548","name":"\u0110\u1ea1i h\u1ecdc Qu\u1ed1c gia H\u00e0 N\u1ed9i","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015548","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015501","name":"Qu\u1ef9 \u0110\u1ed5i m\u1edbi s\u00e1ng t\u1ea1o Vingroup","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015501","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":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.115843","type":"journal-article","created":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:12:30Z","timestamp":1774714350000},"page":"115843","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Structured exploration and exploitation of label functions for automated data annotation"],"prefix":"10.1016","volume":"342","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5745-3361","authenticated-orcid":false,"given":"Phong","family":"Lam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4927-4761","authenticated-orcid":false,"given":"Ha-Linh","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3596-2352","authenticated-orcid":false,"given":"Thu-Trang","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8970-9870","authenticated-orcid":false,"given":"Son","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9407-1971","authenticated-orcid":false,"given":"Hieu","family":"Dinh Vo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/j.knosys.2026.115843_bib0001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3711118","article-title":"Data-centric artificial intelligence: a survey","volume":"57","author":"Zha","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.knosys.2026.115843_bib0002","series-title":"Overview and importance of data quality for machine learning tasks","first-page":"3561","author":"Jain","year":"2020"},{"key":"10.1016\/j.knosys.2026.115843_bib0003","doi-asserted-by":"crossref","unstructured":"S. Wang, Y. Liu, Y. Xu, C. Zhu, M. Zeng, Want to reduce labeling cost? GPT-3 can help, (2021).","DOI":"10.18653\/v1\/2021.findings-emnlp.354"},{"key":"10.1016\/j.knosys.2026.115843_bib0004","doi-asserted-by":"crossref","unstructured":"X. He, Z. Lin, Y. Gong, A. Jin, H. Zhang, C. Lin, J. Jiao, S.M. Yiu, N. Duan, W. Chen, et al., Annollm: making large language models to be better crowdsourced annotators, (2023).","DOI":"10.18653\/v1\/2024.naacl-industry.15"},{"key":"10.1016\/j.knosys.2026.115843_bib0005","unstructured":"B. Settles, Active learning literature survey(2009)."},{"issue":"10s","key":"10.1016\/j.knosys.2026.115843_bib0006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3510414","volume":"54","author":"Liu","year":"2022","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"9","key":"10.1016\/j.knosys.2026.115843_bib0007","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3472291","article-title":"A survey of deep active learning","volume":"54","author":"Ren","year":"2021","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"10.1016\/j.knosys.2026.115843_bib0008","unstructured":"N. Guan, N. Koudas, Activedp: bridging active learning and data programming, (2024)."},{"key":"10.1016\/j.knosys.2026.115843_bib0009","series-title":"2018 IEEE International Conference on Big Data (Big Data)","first-page":"46","article-title":"Hybridization of active learning and data programming for labeling large industrial datasets","author":"Nashaat","year":"2018"},{"key":"10.1016\/j.knosys.2026.115843_bib0010","first-page":"51955","article-title":"Promises and pitfalls of threshold-based auto-labeling","volume":"36","author":"Vishwakarma","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115843_bib0011","series-title":"Label propagation through linear neighborhoods","first-page":"985","author":"Wang","year":"2006"},{"issue":"3","key":"10.1016\/j.knosys.2026.115843_bib0012","article-title":"Semi-supervised learning","volume":"20","author":"Chapelle","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"key":"10.1016\/j.knosys.2026.115843_bib0013","article-title":"Learning with local and global consistency","volume":"16","author":"Zhou","year":"2003","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115843_bib0014","article-title":"Data programming: creating large training sets, quickly","volume":"29","author":"Ratner","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115843_bib0015","series-title":"International Conference on Machine Learning","first-page":"3280","article-title":"Fast and three-rious: speeding up weak supervision with triplet methods","author":"Fu","year":"2020"},{"key":"10.1016\/j.knosys.2026.115843_bib0016","series-title":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","first-page":"1717","author":"Das","year":"2020"},{"key":"10.1016\/j.knosys.2026.115843_bib0017","unstructured":"B. Boecking, W. Neiswanger, E. Xing, A. Dubrawski, Interactive weak supervision: learning useful heuristics for data labeling, (2020)."},{"key":"10.1016\/j.knosys.2026.115843_bib0018","first-page":"269","volume":"11","author":"Ratner","year":"2017"},{"issue":"4","key":"10.1016\/j.knosys.2026.115843_bib0019","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3725730","article-title":"CPWS: confident programmatic weak supervision for high-quality data labeling","volume":"43","author":"Ruan","year":"2025","journal-title":"ACM Trans. Inf. Syst."},{"key":"10.1016\/j.knosys.2026.115843_bib0020","first-page":"122292","volume":"37","author":"Zhang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115843_bib0021","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115843_bib0022","doi-asserted-by":"crossref","unstructured":"J. Ye, J. Gao, Q. Li, H. Xu, J. Feng, Z. Wu, T. Yu, L. Kong, Zerogen: efficient zero-shot learning via dataset generation, (2022).","DOI":"10.18653\/v1\/2022.emnlp-main.801"},{"key":"10.1016\/j.knosys.2026.115843_bib0023","series-title":"International Conference on Machine Learning","first-page":"24457","article-title":"Tuning language models as training data generators for augmentation-enhanced few-shot learning","author":"Meng","year":"2023"},{"key":"10.1016\/j.knosys.2026.115843_bib0024","doi-asserted-by":"crossref","unstructured":"R. Zhang, Y. Li, Y. Ma, M. Zhou, L. Zou, Llmaaa: making large language models as active annotators, (2023).","DOI":"10.18653\/v1\/2023.findings-emnlp.872"},{"key":"10.1016\/j.knosys.2026.115843_bib0025","series-title":"Findings of the Association for Computational Linguistics: ACL 2025","first-page":"25771","article-title":"Just put a human in the loop? investigating LLM-assisted annotation for subjective tasks","author":"Schroeder","year":"2025"},{"key":"10.1016\/j.knosys.2026.115843_bib0026","article-title":"Reliable programmatic weak supervision with confidence intervals for label probabilities","author":"Mazuelas","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115843_bib0027","series-title":"Proceedings of the VLDB Endowment. International Conference on Very Large Data Bases","first-page":"223","volume":"12","author":"Varma","year":"2018"},{"key":"10.1016\/j.knosys.2026.115843_bib0028","doi-asserted-by":"crossref","unstructured":"X. Zhao, H. Ding, Z. Feng, GLaRA: graph-based labeling rule augmentation for weakly supervised named entity recognition, (2021).","DOI":"10.18653\/v1\/2021.eacl-main.318"},{"key":"10.1016\/j.knosys.2026.115843_bib0029","first-page":"62648","volume":"37","author":"Huang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115843_bib0030","first-page":"25","author":"Guan","year":"2025"},{"key":"10.1016\/j.knosys.2026.115843_bib0031","series-title":"Refining labeling functions with limited labeled data","first-page":"1318","author":"Li","year":"2025"},{"issue":"2","key":"10.1016\/j.knosys.2026.115843_bib0032","first-page":"1","article-title":"Language models in the loop: incorporating prompting into weak supervision","volume":"1","author":"Smith","year":"2024","journal-title":"ACM\/JMS J. Data S."},{"key":"10.1016\/j.knosys.2026.115843_bib0033","first-page":"384","author":"Alvarez","year":"2025"},{"key":"10.1016\/j.knosys.2026.115843_bib0034","series-title":"2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA)","first-page":"138","author":"Alberto","year":"2015"},{"key":"10.1016\/j.knosys.2026.115843_bib0035","series-title":"Contributions to the study of SMS spam filtering: new collection and results","first-page":"259","author":"Almeida","year":"2011"},{"key":"10.1016\/j.knosys.2026.115843_bib0036","doi-asserted-by":"crossref","unstructured":"W. Ren, Y. Li, H. Su, D. Kartchner, C. Mitchell, C. Zhang, Denoising multi-source weak supervision for neural text classification, (2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.334"},{"issue":"4","key":"10.1016\/j.knosys.2026.115843_bib0037","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1002\/asi.23062","volume":"65","author":"Malo","year":"2014","journal-title":"J. Assoc. Inf. Sci. Technol."},{"key":"10.1016\/j.knosys.2026.115843_bib0038","series-title":"Overview of the BioCreative VI chemical-protein interaction track","first-page":"141","volume":"1","author":"Krallinger","year":"2017"},{"key":"10.1016\/j.knosys.2026.115843_bib0039","unstructured":"L. Phong, N. Ha-Linh, N. Thu-Trang, N. Son, D.V. Hieu, Structured exploration and exploitation of label functions for automated data annotation, https:\/\/github.com\/iSE-UET-VNU\/EXPONA."},{"key":"10.1016\/j.knosys.2026.115843_bib0040","first-page":"14229","author":"Zhu","year":"2023"},{"issue":"1","key":"10.1016\/j.knosys.2026.115843_bib0041","first-page":"20","article-title":"Maximum likelihood estimation of observer error-rates using the EM algorithm","volume":"28","author":"Dawid","year":"1979","journal-title":"J. Royal Stat. Soc."},{"key":"10.1016\/j.knosys.2026.115843_bib0042","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","author":"Devlin","year":"2019"},{"key":"10.1016\/j.knosys.2026.115843_bib0043","doi-asserted-by":"crossref","unstructured":"J. Li, H. Ding, J. Shang, J. McAuley, Z. Feng, Weakly supervised named entity tagging with learnable logical rules, (2021).","DOI":"10.18653\/v1\/2021.acl-long.352"},{"key":"10.1016\/j.knosys.2026.115843_bib0044","unstructured":"B. Boecking, W. Neiswanger, E. Xing, A. Dubrawski, Interactive weak supervision: learning useful heuristics for data labeling, (2020)."},{"key":"10.1016\/j.knosys.2026.115843_bib0045","series-title":"Adaptive rule discovery for labeling text data","first-page":"2217","author":"Galhotra","year":"2021"},{"issue":"2","key":"10.1016\/j.knosys.2026.115843_bib0046","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1007\/s10506-023-09388-1","article-title":"Combining prompt-based language models and weak supervision for labeling named entity recognition on legal documents: V. Oliveira et al","volume":"33","author":"Oliveira","year":"2025","journal-title":"Artif. Intell. Law"},{"key":"10.1016\/j.knosys.2026.115843_bib0047","first-page":"15983","article-title":"Pearls from pebbles: improved confidence functions for auto-labeling","volume":"37","author":"Vishwakarma","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115843_bib0048","article-title":"Leveraging local and global relationships for corrupted label detection","volume":"166","author":"Lam","year":"2025","journal-title":"Fut. Gen. Comput. Syst."},{"key":"10.1016\/j.knosys.2026.115843_bib0049","series-title":"International Conference on Machine Learning","first-page":"27412","article-title":"Detecting corrupted labels without training a model to predict","author":"Zhu","year":"2022"},{"key":"10.1016\/j.knosys.2026.115843_bib0050","first-page":"1345","author":"Yin","year":"2023"},{"key":"10.1016\/j.knosys.2026.115843_bib0051","series-title":"Delving into instance-dependent label noise in graph data: a comprehensive study and benchmark","first-page":"5539","author":"Kim","year":"2025"},{"key":"10.1016\/j.knosys.2026.115843_bib0052","unstructured":"A. Maharana, P. Yadav, M. Bansal, D2 pruning: message passing for balancing diversity & difficulty in data pruning, in: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.knosys.2026.115843_bib0053","series-title":"2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)","first-page":"289","article-title":"Synthetic data augmentation using GAN for improved liver lesion classification","author":"Frid-Adar","year":"2018"},{"issue":"3","key":"10.1016\/j.knosys.2026.115843_bib0054","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3381028","article-title":"Outlier detection: methods, models, and classification","volume":"53","author":"Boukerche","year":"2020","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"2","key":"10.1016\/j.knosys.2026.115843_bib0055","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.1007\/s10462-019-09709-4","article-title":"Missing value imputation: a review and analysis of the literature (2006\u20132017)","volume":"53","author":"Lin","year":"2020","journal-title":"Artif. Intell. Rev."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005691?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005691?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:18:56Z","timestamp":1777569536000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126005691"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":55,"alternative-id":["S0950705126005691"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115843","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Structured exploration and exploitation of label functions for automated data annotation","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115843","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":"115843"}}