{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:54:40Z","timestamp":1772934880378,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11401628","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"2405-2414","source":"Crossref","is-referenced-by-count":0,"title":["LLM on a Budget: Active Knowledge Distillation for Efficient Classification of Large Text Corpora"],"prefix":"10.1109","author":[{"given":"Viviana","family":"Luccioli","sequence":"first","affiliation":[{"name":"Board of Governors of the Federal Reserve System"}]},{"given":"Rithika","family":"Iyengar","sequence":"additional","affiliation":[{"name":"Board of Governors of the Federal Reserve System"}]},{"given":"Ryan","family":"Panley","sequence":"additional","affiliation":[{"name":"Board of Governors of the Federal Reserve System"}]},{"given":"Flora","family":"Haberkorn","sequence":"additional","affiliation":[{"name":"Board of Governors of the Federal Reserve System"}]},{"given":"Xiaoyu","family":"Ge","sequence":"additional","affiliation":[{"name":"Board of Governors of the Federal Reserve System"}]},{"given":"Leland","family":"Crane","sequence":"additional","affiliation":[{"name":"Board of Governors of the Federal Reserve System"}]},{"given":"Nitish","family":"Sinha","sequence":"additional","affiliation":[{"name":"Board of Governors of the Federal Reserve System"}]},{"given":"Seung Jung","family":"Lee","sequence":"additional","affiliation":[{"name":"Board of Governors of the Federal Reserve System"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.2010.01625.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24148\/wp2017-01"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref4","volume-title":"Advancements in natural language processing: Exploring transformer-based architectures for text understanding","author":"Wu","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.29172\/7c2a6982-6d72-4cd8-bba6-2fccb06a7011"},{"key":"ref8","volume-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref9","volume-title":"A survey of knowledge distillation in natural language processing","author":"Ghorbani","year":"2020"},{"key":"ref10","first-page":"153","article-title":"Distilling task-specific knowledge from bert into simple neural networks","volume-title":"Proceedings of the 3rd Workshop on Neural Generation and Translation","author":"Tang","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref12","first-page":"999","article-title":"Support vector machine active learning with applications to text classification","volume-title":"Proceedings of the Seventeenth International Conference on Machine Learning, ser. ICML \u201900","author":"Tong","year":"2000"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.638"},{"key":"ref14","volume-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref15","first-page":"4225","article-title":"Distilling reasoning capabilities from large language models","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Findings","author":"Dasgupta","year":"2022"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"122356","DOI":"10.1016\/j.apenergy.2023.122356","article-title":"Integrating active learning and semi-supervised learning for improved data-driven hvac fault diagnosis performance","volume":"356","author":"Fan","year":"2024","journal-title":"Applied Energy"},{"key":"ref17","volume-title":"Active learning literature survey","author":"Settles","year":"2009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_1"},{"issue":"3","key":"ref19","doi-asserted-by":"crossref","DOI":"10.3390\/electronics11030396","article-title":"Uncertainty-based rejection in machine learning: Implications for model development and interpretability","volume":"11","author":"Barandas","year":"2022","journal-title":"Electronics"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3321\/j.issn:0529-6579.2007.z1.029"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref22","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"NIPS","author":"Mikolov","year":"2013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.12"},{"key":"ref25","volume-title":"Synthesis Lectures on Artificial Intelligence and Machine Learning","author":"Brachman","year":"2012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2016.7840657"},{"key":"ref27","article-title":"Robust learning of classification models from noisy soft-label information","volume-title":"ECCV","author":"Xue","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9377741"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.21"},{"key":"ref30","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref31","article-title":"Practical bayesian optimization of machine learning algorithms","volume":"25","author":"Snoek","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref32","volume-title":"Tinybert: Distilling bert for natural language understanding","author":"Jiao","year":"2019"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.neucom.2022.08.061","article-title":"Cross-domain knowledge distillation for text classification","volume":"509","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.emnlp-main.215","volume-title":"Performance-guided llm knowledge distillation for efficient text classification at scale","author":"Palo","year":"2024"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49357.2023.10096950","volume-title":"Adaptive knowledge distillation between text and speech pre-trained models","author":"Ni","year":"2023"},{"key":"ref36","volume-title":"Revisiting knowledge distillation: An inheritance and exploration framework","author":"Yuan","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130417"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_37"},{"key":"ref39","volume-title":"Not all samples are created equal: Deep learning with importance sampling","author":"Katharopoulos","year":"2019"},{"key":"ref40","volume-title":"Task-adaptive pretrained language models via clustered-importance sampling","author":"Grangier","year":"2025"},{"key":"ref41","volume-title":"Active learning for optimal intervention design in causal models","author":"Wang","year":"2023"},{"key":"ref42","volume-title":"Active knowledge distillation","author":"Zhang","year":"2023"},{"key":"ref43","volume-title":"Task-agnostic active learning for final-layer fine-tuning","author":"Kothadiya","year":"2022"},{"key":"ref44","volume-title":"Active knowledge distillation","author":"Kuznetsov","year":"2021"},{"key":"ref45","volume-title":"Active-knowledgedistillation","author":"Chiang","year":"2020"},{"key":"ref46","volume-title":"A survey on data selection for language models","author":"Albalak","year":"2024"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11401628.pdf?arnumber=11401628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:19:15Z","timestamp":1772867955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11401628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11401628","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}