{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:27:48Z","timestamp":1783542468887,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012389","name":"National Research Foundation of Korea (NRF) grant funded by the Korean Government [Ministry of Science and Information and Communications Technology (MSIT)]","doi-asserted-by":"publisher","award":["RS-2025-02214322"],"award-info":[{"award-number":["RS-2025-02214322"]}],"id":[{"id":"10.13039\/501100012389","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP)-Information Technology Research Center (ITRC) grant funded by the Korean Government","award":["IITP-2026-RS-2022-00156295"],"award-info":[{"award-number":["IITP-2026-RS-2022-00156295"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3705468","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T19:41:23Z","timestamp":1781898083000},"page":"99526-99540","source":"Crossref","is-referenced-by-count":0,"title":["Token-Based Task-Aware Knowledge Distillation for Encoder Adaptation"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2022-5460","authenticated-orcid":false,"given":"Eunjoung","family":"Yoo","sequence":"first","affiliation":[{"name":"Artificial Intelligence Convergence, Ewha Womans University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7691-0930","authenticated-orcid":false,"given":"Jieui","family":"Kang","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Convergence, Ewha Womans University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2458-3048","authenticated-orcid":false,"given":"Soeun","family":"Choi","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Convergence, Ewha Womans University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1882-5230","authenticated-orcid":false,"given":"Yeonhee","family":"Kim","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Convergence, Ewha Womans University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8722-8486","authenticated-orcid":false,"given":"Jaehyeong","family":"Sim","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Ewha Womans University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref2","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref3","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref4","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref7","first-page":"1","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lan"},{"key":"ref8","first-page":"3980","article-title":"Sentence-BERT: Sentence embeddings using Siamese BERT-networks","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process. (EMNLP-IJCNLP)","author":"Reimers"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.104"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref11","article-title":"Passage re-ranking with BERT","author":"Nogueira","year":"2019","journal-title":"arXiv:1901.04085"},{"key":"ref12","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref13","article-title":"Distilling task-specific knowledge from BERT into simple neural networks","author":"Tang","year":"2019","journal-title":"arXiv:1903.12136"},{"key":"ref14","first-page":"878","article-title":"Language-agnostic BERT sentence embedding","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Feng"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad651"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34639"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref20","first-page":"4322","article-title":"Patient knowledge distillation for BERT model compression","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process. 9th Int. Joint Conf. Natural Lang. Process. (EMNLP-IJCNLP)","author":"Sun"},{"key":"ref21","first-page":"4163","article-title":"TinyBERT: Distilling BERT for natural language understanding","volume-title":"Proc. Findings Assoc. Comput. Linguistics, EMNLP","author":"Jiao"},{"key":"ref22","first-page":"8449","article-title":"AD-KD: Attribution-driven knowledge distillation for language model compression","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics","author":"Wu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.30"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.71"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126040"},{"key":"ref26","first-page":"1","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref28","first-page":"1","article-title":"The fifth PASCAL recognizing textual entailment challenge","volume-title":"Proc. TAC Workshop","author":"Bentivogli"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"ref30","first-page":"2140","article-title":"MiniLMv2: Multi-head self-attention relation distillation for compressing pretrained transformers","volume-title":"Proc. Findings Assoc. Comput. Linguistics: ACL-IJCNLP","author":"Wang"},{"key":"ref31","article-title":"Parameter-efficient and student-friendly knowledge distillation","author":"Rao","year":"2022","journal-title":"arXiv:2205.15308"},{"key":"ref32","first-page":"1","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zagoruyko"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.07737"},{"key":"ref38","article-title":"Representation learning with contrastive predictive coding","author":"Van Den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref39","first-page":"1","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref42","first-page":"9","article-title":"Automatically constructing a corpus of sentential paraphrases","volume-title":"Proc. 3rd Int. Workshop Paraphrasing (IWP)","author":"Dolan"},{"key":"ref43","volume-title":"Quora Question Pairs Dataset","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/s17-2001"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/11736790_9"},{"key":"ref47","first-page":"2021","article-title":"Adversarial examples for evaluating reading comprehension systems","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Jia"},{"key":"ref48","first-page":"650","article-title":"Breaking NLI systems with sentences that require simple lexical inferences","volume-title":"Proc. 56th Annu. Meeting Assoc. Comput. Linguistics","author":"Glockner"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11571788.pdf?arnumber=11571788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:44:23Z","timestamp":1783539863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3705468","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}