{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T14:22:40Z","timestamp":1778768560214,"version":"3.51.4"},"reference-count":61,"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\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LDT23F02023F02"],"award-info":[{"award-number":["LDT23F02023F02"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276230"],"award-info":[{"award-number":["62276230"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72350710798"],"award-info":[{"award-number":["72350710798"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133657","type":"journal-article","created":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T16:31:03Z","timestamp":1776011463000},"page":"133657","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Improving few-shot named entity recognition with distilled knowledge from large language model"],"prefix":"10.1016","volume":"685","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4729-0289","authenticated-orcid":false,"given":"Qi","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2361-8842","authenticated-orcid":false,"given":"Tingyu","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Jiayuan","family":"Su","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6118-6505","authenticated-orcid":false,"given":"Hongwei","family":"Wang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133657_bib0005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neucom.2019.11.072","article-title":"Improving named entity recognition in noisy user-generated text with local distance neighbor feature","volume":"382","author":"Al-Nabki","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133657_bib0010","doi-asserted-by":"crossref","first-page":"29","DOI":"10.58496\/MJBD\/2023\/004","article-title":"Transfer learning: a new promising technique","volume":"2023","author":"Ali","year":"2023","journal-title":"Mesopotamian Journal of Big Data"},{"key":"10.1016\/j.neucom.2026.133657_bib0015","series-title":"Advances in Neural Information Processing Systems","first-page":"1877","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"10.1016\/j.neucom.2026.133657_bib0020","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"5711","article-title":"Few-shot named entity recognition with self-describing networks","author":"Chen","year":"2022"},{"key":"10.1016\/j.neucom.2026.133657_bib0025","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1016\/j.neucom.2022.11.064","article-title":"Semi-supervised named entity recognition in multi-level contexts","volume":"520","author":"Chen","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133657_bib0030","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.neucom.2022.04.059","article-title":"A pattern-first pipeline approach for entity and relation extraction","volume":"494","author":"Chen","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133657_bib0035","author":"Chia"},{"key":"10.1016\/j.neucom.2026.133657_bib0040","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.133657_bib0045","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"7183","article-title":"SpanNER: named entity re-\/recognition as span prediction","author":"Fu","year":"2021"},{"key":"10.1016\/j.neucom.2026.133657_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127064","article-title":"Dodfminer: an automated tool for named entity recognition from official gazettes","volume":"568","author":"Guimar\u00e3es","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133657_bib0055","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"14852","article-title":"Large language models are reasoning teachers","author":"Ho","year":"2023"},{"key":"10.1016\/j.neucom.2026.133657_bib0060","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","first-page":"8003","article-title":"Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes","author":"Hsieh","year":"2023"},{"key":"10.1016\/j.neucom.2026.133657_bib0065","series-title":"International Conference on Learning Representations","article-title":"Lora: low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"10.1016\/j.neucom.2026.133657_bib0070","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.neucom.2020.09.077","article-title":"Hypergraph network model for nested entity mention recognition","volume":"423","author":"Huang","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133657_bib0075","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"10408","article-title":"Few-shot named entity recognition: an empirical baseline study","author":"Huang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133657_bib0080","series-title":"Advances in Neural Information Processing Systems","article-title":"Weighted distillation with unlabeled examples","author":"Iliopoulos","year":"2022"},{"key":"10.1016\/j.neucom.2026.133657_bib0085","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae163","article-title":"Advancing entity recognition in biomedicine via instruction tuning of large language models","volume":"40","author":"Keloth","year":"2024","journal-title":"Bioinformatics"},{"key":"10.1016\/j.neucom.2026.133657_bib0090","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133657_bib0095","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.neucom.2021.08.094","article-title":"A segment enhanced span-based model for nested named entity recognition","volume":"465","author":"Li","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133657_bib0100","doi-asserted-by":"crossref","first-page":"4245","DOI":"10.1109\/TKDE.2020.3038670","article-title":"Few-shot named entity recognition via meta-learning","volume":"34","author":"Li","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.133657_bib0105","first-page":"10965","article-title":"Unified named entity recognition as word-word relation classification","volume":"36","author":"Li","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.133657_bib0110","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/TKDE.2020.2981314","article-title":"A survey on deep learning for named entity recognition","volume":"34","author":"Li","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.133657_bib0115","series-title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25","first-page":"8168","article-title":"Multimodal knowledge retrieval-augmented iterative alignment for satellite commonsense conversation","author":"Li","year":"2025"},{"key":"10.1016\/j.neucom.2026.133657_bib0120","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1016\/j.neucom.2022.07.012","article-title":"Handling negative samples problems in span-based nested named entity recognition","volume":"505","author":"Liu","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133657_bib0125","series-title":"Proceedings of Deep Learning Inside Out (DeeLIO 2022): the 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures","first-page":"100","article-title":"What makes good in-context examples for GPT-3?","author":"Liu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133657_bib0130","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1162\/tacl_a_00638","article-title":"Lost in the middle: how language models use long contexts","volume":"12","author":"Liu","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.neucom.2026.133657_bib0135","author":"Longpre"},{"key":"10.1016\/j.neucom.2026.133657_bib0140","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"5755","article-title":"Unified structure generation for universal information extraction","author":"Lu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133657_bib0145","doi-asserted-by":"crossref","first-page":"247","DOI":"10.58496\/MJCSC\/2025\/016","article-title":"Self-attention enhanced dual BiGRU for arabic fake news detection","volume":"2025","author":"Merzah","year":"2025","journal-title":"Mesopotamian Journal of Computer Science"},{"key":"10.1016\/j.neucom.2026.133657_bib0150","doi-asserted-by":"crossref","first-page":"1980","DOI":"10.1109\/TASLP.2024.3372879","article-title":"Decomposed meta-learning for few-shot sequence labeling","volume":"32","author":"Ma","year":"2024","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.neucom.2026.133657_bib0155","series-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"1064","article-title":"End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF","author":"Ma","year":"2016"},{"key":"10.1016\/j.neucom.2026.133657_bib0160","series-title":"Proceedings of the 27th International Conference on Computational Linguistics","first-page":"711","article-title":"An empirical study on fine-grained named entity recognition","author":"Mai","year":"2018"},{"key":"10.1016\/j.neucom.2026.133657_bib0165","series-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"2791","article-title":"MetaICL: learning to learn in context","author":"Min","year":"2022"},{"key":"10.1016\/j.neucom.2026.133657_bib0170","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"11048","article-title":"Rethinking the role of demonstrations: what makes in-context learning work?","author":"Min","year":"2022"},{"key":"10.1016\/j.neucom.2026.133657_bib0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111688","article-title":"Few-shot nested named entity recognition","volume":"293","author":"Ming","year":"2024","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.133657_bib0185","series-title":"Proceedings of the Seventeenth Conference on Computational Natural Language Learning","first-page":"143","article-title":"Towards robust linguistic analysis using OntoNotes","author":"Pradhan","year":"2013"},{"key":"10.1016\/j.neucom.2026.133657_bib0190","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.133657_bib0195","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing","article-title":"Sentence-bert: sentence embeddings using siamese bert-networks","author":"Reimers","year":"2019"},{"key":"10.1016\/j.neucom.2026.133657_bib0200","series-title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17","first-page":"2662","article-title":"Right for the right reasons: training differentiable models by constraining their explanations","author":"Ross","year":"2017"},{"key":"10.1016\/j.neucom.2026.133657_bib0205","doi-asserted-by":"crossref","first-page":"42","DOI":"10.58496\/BJML\/2025\/004","article-title":"Enhancing semantic image retrieval using self-supervised learning: a label-efficient approach","volume":"2025","author":"Sallam","year":"2025","journal-title":"Babylon. J. Mach. Learn."},{"key":"10.1016\/j.neucom.2026.133657_bib0210","doi-asserted-by":"crossref","first-page":"6415","DOI":"10.1007\/s10489-024-05492-0","article-title":"Aspect based sentiment analysis with instruction tuning and external knowledge enhanced dependency graph","volume":"54","author":"Shi","year":"2024","journal-title":"Appl. Intell."},{"key":"10.1016\/j.neucom.2026.133657_bib0215","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","first-page":"7059","article-title":"Distilling reasoning capabilities into smaller language models","author":"Shridhar","year":"2023"},{"key":"10.1016\/j.neucom.2026.133657_bib0220","author":"Smith"},{"key":"10.1016\/j.neucom.2026.133657_bib0225","author":"Taori"},{"key":"10.1016\/j.neucom.2026.133657_bib0230","series-title":"Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003","first-page":"142","article-title":"Introduction to the conll-2003 shared task: language-independent named entity recognition","author":"Tjong Kim Sang","year":"2003"},{"key":"10.1016\/j.neucom.2026.133657_bib0235","author":"Touvron"},{"key":"10.1016\/j.neucom.2026.133657_bib0240","doi-asserted-by":"crossref","DOI":"10.1093\/jamia\/ocae122","article-title":"BioInstruct: instruction tuning of large language models for biomedical natural language processing","author":"Tran","year":"2024","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.neucom.2026.133657_bib0245","series-title":"Ace 2005 Multilingual Training Corpus-Linguistic Data Consortium","author":"Walker","year":"2005"},{"key":"10.1016\/j.neucom.2026.133657_bib0250","author":"Wan"},{"key":"10.1016\/j.neucom.2026.133657_bib0255","author":"Wang"},{"key":"10.1016\/j.neucom.2026.133657_bib0260","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"5918","article-title":"Pyramid: a layered model for nested named entity recognition","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133657_bib0265","author":"Wang"},{"key":"10.1016\/j.neucom.2026.133657_bib0270","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25\u201329, 2022","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2022"},{"key":"10.1016\/j.neucom.2026.133657_bib0275","series-title":"Advances in Neural Information Processing Systems","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022"},{"key":"10.1016\/j.neucom.2026.133657_bib0280","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1162\/dint_a_00195","article-title":"Few-shot named entity recognition with joint token and sentence awareness","volume":"5","author":"Wen","year":"2023","journal-title":"Data Intelligence"},{"key":"10.1016\/j.neucom.2026.133657_bib0285","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.neucom.2019.09.005","article-title":"Incorporating token-level dictionary feature into neural model for named entity recognition","volume":"375","author":"Xiaofeng","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133657_bib0290","author":"Xu"},{"key":"10.1016\/j.neucom.2026.133657_bib0295","doi-asserted-by":"crossref","first-page":"150","DOI":"10.58496\/ADSA\/2023\/014","article-title":"Does lack of knowledge and hardship of information access signify powerful AI? A large language model perspective","volume":"2023","author":"Zahid","year":"2023","journal-title":"Appl. Data Sci. Anal."},{"key":"10.1016\/j.neucom.2026.133657_bib0300","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111730","article-title":"Ceptner: contrastive learning enhanced prototypical network for two-stage few-shot named entity recognition","volume":"295","author":"Zha","year":"2024","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.133657_bib0305","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127938","article-title":"Improving few-shot named entity recognition via semantics induced optimal transport","volume":"597","author":"Zhou","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133657_bib0310","author":"Zhou"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010544?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010544?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T13:55:28Z","timestamp":1778766928000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226010544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":61,"alternative-id":["S0925231226010544"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133657","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Improving few-shot named entity recognition with distilled knowledge from large language model","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133657","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":"133657"}}