{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T18:10:09Z","timestamp":1751047809470,"version":"3.41.0"},"reference-count":58,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T00:00:00Z","timestamp":1750982400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Large language models (LLMs) have demonstrated remarkable performance across various linguistic tasks. However, existing LLMs perform inadequately in information extraction tasks for both Chinese and English. Numerous studies attempt to enhance model performance by increasing the scale of training data. However, discrepancies in the number and type of schemas used during training and evaluation can harm model effectiveness. To tackle this challenge, we propose ChunkUIE, a unified information extraction model that supports Chinese and English. We design a chunked instruction construction strategy that randomly and reproducibly divides all schemas into chunks containing an identical number of schemas. This approach ensures that the union of schemas across all chunks encompasses all schemas. By limiting the number of schemas in each instruction, this strategy effectively addresses the performance degradation caused by inconsistencies in schema counts between training and evaluation. Additionally, we construct some challenging negative schemas using a predefined hard schema dictionary, which mitigates the model\u2019s semantic confusion regarding similar schemas. Experimental results demonstrate that ChunkUIE enhances zero-shot performance in information extraction.<\/jats:p>","DOI":"10.1371\/journal.pone.0326764","type":"journal-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T17:37:18Z","timestamp":1751045838000},"page":"e0326764","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["ChunkUIE: Chunked instruction-based unified information extraction"],"prefix":"10.1371","volume":"20","author":[{"given":"Wei","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingzhen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinling","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9602-8870","authenticated-orcid":true,"given":"Wei","family":"Men","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,6,27]]},"reference":[{"key":"pone.0326764.ref001","doi-asserted-by":"crossref","first-page":"15406","DOI":"10.18653\/v1\/2023.acl-long.859","article-title":"Prompting PaLM for translation: assessing strategies and performance.","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"D Vilar","year":"2023"},{"key":"pone.0326764.ref002","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.1109\/BigData59044.2023.10386743","article-title":"Multimodal large language models: a survey.","volume-title":"2023 IEEE International Conference on Big Data (BigData)","author":"J Wu","year":"2023"},{"issue":"2","key":"pone.0326764.ref003","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0298974","article-title":"Research on joint model relation extraction method based on entity mapping","volume":"19","author":"H Tang","year":"2024","journal-title":"PLoS One"},{"issue":"2","key":"pone.0326764.ref004","article-title":"Span-based single-stage joint entity-relation extraction model","volume":"18","author":"D Han","year":"2023","journal-title":"PLoS One"},{"key":"pone.0326764.ref005","unstructured":"Li B, Fang G, Yang Y, Wang Q, Ye W, Zhao W. Evaluating ChatGPT\u2019s information extraction capabilities: an assessment of performance, explainability, calibration, and faithfulness. arXiv preprint 2023. https:\/\/arxiv.org\/abs\/2304.11633"},{"key":"pone.0326764.ref006","doi-asserted-by":"crossref","unstructured":"Xu D, Chen W, Peng W, Zhang C, Xu T, Zhao X. Large language models for generative information extraction: a survey. arXiv preprint 2024. https:\/\/arxiv.org\/abs\/2312.17617","DOI":"10.1007\/s11704-024-40555-y"},{"key":"pone.0326764.ref007","unstructured":"Wang S, Sun X, Li X, Ouyang R, Wu F, Zhang T. GPT-NER: named entity recognition via large language models. arXiv preprint 2023. https:\/\/arxiv.org\/abs\/2304.10428"},{"key":"pone.0326764.ref008","doi-asserted-by":"crossref","first-page":"15339","DOI":"10.18653\/v1\/2023.acl-long.855","article-title":"CodeIE: Large code generation models are better few-shot information extractors.","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"P Li","year":"2023"},{"key":"pone.0326764.ref009","article-title":"Unified structure generation for universal information extraction","author":"Y Lu","year":"2022","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref010","article-title":"Instructuie: multi-task instruction tuning for unified information extraction","author":"X Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref011","article-title":"Qwen2 technical report","author":"A Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref012","article-title":"The Llama 3 herd of models","author":"A Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref013","author":"EJ Hu","year":"2022"},{"issue":"70","key":"pone.0326764.ref014","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"HW Chung","year":"2024","journal-title":"J Mach Learn Res"},{"key":"pone.0326764.ref015","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"L Ouyang","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"pone.0326764.ref016","article-title":"YAYI-UIE: a chat-enhanced instruction tuning framework for universal information extraction","author":"X Xiao","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref017","article-title":"Baichuan 2: open large-scale language models","author":"A Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref018","first-page":"13318","article-title":"Universal information extraction as unified semantic matching.","volume-title":"Proceedings of the AAAI conference on Artificial Intelligence","author":"J Lou","year":"2023"},{"key":"pone.0326764.ref019","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1007\/978-3-642-15939-8_10","volume-title":"Machine learning and knowledge discovery in databases","author":"S Riedel","year":"2010"},{"key":"pone.0326764.ref020","doi-asserted-by":"crossref","first-page":"142","DOI":"10.3115\/1119176.1119195","article-title":"Introduction to the CoNLL-2003 shared task: language-independent named entity recognition.","volume-title":"Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003","author":"EF Tjong Kim Sang","year":"2003"},{"key":"pone.0326764.ref021","doi-asserted-by":"crossref","first-page":"3219","DOI":"10.18653\/v1\/D18-1360","article-title":"Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction.","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Y Luan","year":"2018"},{"key":"pone.0326764.ref022","article-title":"InstructIE: a bilingual instruction-based information extraction dataset","author":"H Gui","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref023","first-page":"127","article-title":"IEPile: unearthing large scale schema-conditioned information extraction corpus.","author":"H Gui","year":"2024","journal-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics"},{"key":"pone.0326764.ref024","article-title":"KnowCoder: coding structured knowledge into LLMs for universal information extraction","author":"Z Li","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref025","article-title":"InstructUIE: multi-task instruction tuning for unified information extraction","author":"X Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref026","first-page":"11","article-title":"OntoNotes: The 90% Solution.","volume-title":"Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Tutorial Abstracts","author":"SS Pradhan","year":"2009"},{"key":"pone.0326764.ref027","doi-asserted-by":"crossref","first-page":"801","DOI":"10.18653\/v1\/2022.findings-naacl.60","article-title":"MultiNERD: a multilingual, multi-genre and fine-grained dataset for named entity recognition (and disambiguation).","volume-title":"Findings of the Association for Computational Linguistics: NAACL 2022","author":"S Tedeschi","year":"2022"},{"key":"pone.0326764.ref028","doi-asserted-by":"crossref","first-page":"8386","DOI":"10.1109\/ICASSP.2013.6639301","article-title":"Asgard: a portable architecture for multilingual dialogue systems.","volume-title":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"J Liu","year":"2013"},{"key":"pone.0326764.ref029","first-page":"3329","article-title":"Crossroads, buildings and neighborhoods: a dataset for fine-grained location recognition.","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"P Chen","year":"2022"},{"key":"pone.0326764.ref030","article-title":"Genia corpus\u2014a semantically annotated corpus for bio-textmining","volume":"19","author":"JD Kim","year":"2003","journal-title":"Bioinformatics"},{"key":"pone.0326764.ref031","first-page":"635","article-title":"Biomedical named entity recognition at scale.","volume-title":"Pattern recognition","author":"V Kocaman","year":"2021"},{"key":"pone.0326764.ref032","article-title":"Optimizing bi-encoder for named entity recognition via contrastive learning","author":"S Zhang","year":"2022","journal-title":"arXiv preprint"},{"issue":"6","key":"pone.0326764.ref033","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1093\/bioinformatics\/btt580","article-title":"Anatomical entity mention recognition at literature scale","volume":"30","author":"S Pyysalo","year":"2014","journal-title":"Bioinformatics"},{"key":"pone.0326764.ref034","first-page":"108","article-title":"The third international chinese language processing bakeoff: word segmentation and named entity recognition.","volume-title":"Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing","author":"GA Levow","year":"2006"},{"key":"pone.0326764.ref035","first-page":"1554","article-title":"Chinese NER using lattice LSTM.","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Melbourne, Australia: Association for Computational Linguistics","author":"Y Zhang","year":"2018"},{"key":"pone.0326764.ref036","article-title":"CLUENER2020: fine-grained named entity recognition dataset and benchmark for Chinese","author":"L Xu","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref037","first-page":"33","article-title":"SemEval-2010 task 8: multi-way classification of semantic relations between pairs of nominals.","volume-title":"Proceedings of the 5th International Workshop on Semantic Evaluation","author":"I Hendrickx","year":"2010"},{"key":"pone.0326764.ref038","first-page":"89","article-title":"Introduction to the CoNLL-2004 shared task: semantic role labeling.","volume-title":"Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL-2004) at HLT-NAACL 2004","author":"X Carreras","year":"2004"},{"key":"pone.0326764.ref039","first-page":"7072","article-title":"A hierarchical framework for relation extraction with reinforcement learning","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"R Takanobu","year":"2019"},{"key":"pone.0326764.ref040","doi-asserted-by":"crossref","first-page":"3940","DOI":"10.18653\/v1\/2023.findings-emnlp.259","article-title":"2INER: instructive and in-context learning on few-shot named entity recognition.","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2023. Singapore: Association for Computational Linguistics","author":"J Zhang","year":"2023"},{"key":"pone.0326764.ref041","article-title":"Improving distantly supervised relation extraction using word and entity based attention","author":"S Jat","year":"2018","journal-title":"arXiv preprint"},{"issue":"1","key":"pone.0326764.ref042","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/2041-1480-3-15","article-title":"Extraction of potential adverse drug events from medical case reports","volume":"3","author":"H Gurulingappa","year":"2012","journal-title":"J Biomed Semantics"},{"key":"pone.0326764.ref043","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1007\/978-3-030-60450-9_22","article-title":"CMeIE: construction and evaluation of chinese medical information extraction dataset.","volume-title":"Natural language processing and chinese computing","author":"T Guan","year":"2020"},{"key":"pone.0326764.ref044","doi-asserted-by":"crossref","first-page":"5571","DOI":"10.18653\/v1\/2022.emnlp-main.376","article-title":"PHEE: a dataset for pharmacovigilance event extraction from text.","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Z Sun","year":"2022"},{"key":"pone.0326764.ref045","first-page":"8749","article-title":"Casie: Extracting cybersecurity event information from text.","volume-title":"Proceedings of the AAAI conference on artificial intelligence","author":"T Satyapanich","year":"2020"},{"key":"pone.0326764.ref046","first-page":"534","article-title":"DuEE: a large-scale dataset for chinese event extraction in real-world scenarios.","volume-title":"Natural language processing and chinese computing","author":"X Li","year":"2020"},{"key":"pone.0326764.ref047","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1007\/978-3-031-17120-8_14","article-title":"DuEE-Fin: a large-scale dataset for document-level event extraction.","volume-title":"Natural language processing and chinese computing","author":"C Han","year":"2022"},{"key":"pone.0326764.ref048","first-page":"13452","article-title":"Crossner: Evaluating cross-domain named entity recognition.","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Z Liu","year":"2021"},{"key":"pone.0326764.ref049","doi-asserted-by":"crossref","first-page":"548","DOI":"10.18653\/v1\/D15-1064","article-title":"Named entity recognition for chinese social media with jointly trained embeddings.","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"N Peng","year":"2015"},{"key":"pone.0326764.ref050","doi-asserted-by":"crossref","unstructured":"Li S, Ji H, Han J. Document-level event argument extraction by conditional generation. In: Toutanova K, Rumshisky A, Zettlemoyer L, Hakkani-Tur D, Beltagy I, Bethard S, et al., editors. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Online: Association for Computational Linguistics; 2021. p. 894\u2013908. https:\/\/aclanthology.org\/2021.naacl-main.69","DOI":"10.18653\/v1\/2021.naacl-main.69"},{"key":"pone.0326764.ref051","article-title":"Multi-sentence argument linking","author":"S Ebner","year":"2019","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref052","first-page":"465","article-title":"CrudeOilNews: an annotated crude oil news corpus for event extraction.","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","author":"M Lee","year":"2022"},{"key":"pone.0326764.ref053","first-page":"14638","article-title":"What the role is vs. what plays the role: semi-supervised event argument extraction via dual question answering.","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Y Zhou","year":"2021"},{"key":"pone.0326764.ref054","doi-asserted-by":"crossref","first-page":"4803","DOI":"10.18653\/v1\/D18-1514","article-title":"FewRel: a large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation.","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"X Han","year":"2018"},{"key":"pone.0326764.ref055","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/978-3-030-32236-6_9","article-title":"Ipre: a dataset for inter-personal relationship extraction.","volume-title":"Natural Language Processing and Chinese Computing: 8th CCF International Conference, NLPCC 2019, Dunhuang, China, October 9\u201314, 2019, Proceedings","author":"H Wang","year":"2019"},{"key":"pone.0326764.ref056","article-title":"Llama 2: open foundation and fine-tuned chat models","author":"H Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref057","article-title":"Qwen technical report","author":"J Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"pone.0326764.ref058","article-title":"Mistral 7B","author":"AQ Jiang","year":"2023","journal-title":"arXiv preprint"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0326764","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T17:37:36Z","timestamp":1751045856000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0326764"}},"subtitle":[],"editor":[{"given":"Malte","family":"Rehbein","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,27]]},"references-count":58,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0326764","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,27]]}}}