{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T08:56:07Z","timestamp":1781859367438,"version":"3.54.5"},"reference-count":59,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T00:00:00Z","timestamp":1781827200000},"content-version":"vor","delay-in-days":169,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102372"],"award-info":[{"award-number":["62102372"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004262","name":"Zhengzhou University of Light Industry","doi-asserted-by":"publisher","award":["2021BSJJ029"],"award-info":[{"award-number":["2021BSJJ029"]}],"id":[{"id":"10.13039\/501100004262","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["232102210078"],"award-info":[{"award-number":["232102210078"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"publisher","award":["242300421664"],"award-info":[{"award-number":["242300421664"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>\n                    Entity matching (EM) aims to identify records from different data sources referring to the same real\u2010world entity. Despite remarkable advances with pretrained language models (PLMs), existing PLM\u2010based matchers still encounter significant challenges in effectively integrating external knowledge, representing semantic information at multiple granularities, and handling numerical snippets. To address these challenges, we propose a multigranularity information\u2010enhanced EM method based on collaborative agents (MIEM\u2010CA), featuring three key components: (1) a multiagent information enhancement module (MI) that leverages extensive external knowledge, the decision\u2010making and collaboration capabilities of autonomous agents, and the semantic comprehension power of large language models (LLMs), by integrating attribute selection, web search, and feature extraction agents to improve the completeness of entity representation; (2) a multigranularity semantic encoder (ME) that incrementally captures and integrates token\u2010, attribute\u2010, and entity\u2010level semantics, along with their cross\u2010level correlations, across hierarchical representations spanning the token, attribute, and entity layers (ELs); and (3) a numerical\u2010aware agent module (NA) that employs the chain\u2010of\u2010thought (CoT) strategy to extract numerical information effectively, leverages LLMs to infer the semantic types of these numerical values, and calculates their semantic\u2010aware numerical similarity. Comprehensive experiments on 10 benchmark datasets, which cover structured, dirty, and textual EM settings, demonstrate that, compared with five baseline methods, MIEM\u2010CA achieves an average\n                    <jats:italic>F<\/jats:italic>\n                    <jats:sub>1<\/jats:sub>\n                    score improvement of 6.35% on structured datasets, 9.07% on the dirty datasets, and 8.11% across all datasets.\n                  <\/jats:p>","DOI":"10.1155\/int\/8100559","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T08:29:46Z","timestamp":1781857786000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MIEM\u2010CA: A Multigranularity Information\u2010Enhanced Entity Matching Method Based on Collaborative Agents"],"prefix":"10.1155","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1219-1130","authenticated-orcid":false,"given":"Yaoli","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheran","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuaixi","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongwen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunli","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haojie","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1539-712X","authenticated-orcid":false,"given":"Xiayang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,6,19]]},"reference":[{"key":"e_1_2_12_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.250581"},{"key":"e_1_2_12_2_2","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367564"},{"key":"e_1_2_12_3_2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-31164-2","volume-title":"Data Matching \u2013 Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection","author":"Christen P.","year":"2012"},{"key":"e_1_2_12_4_2","first-page":"3","article-title":"Data Cleaning: Problems and Current Approaches","volume":"23","author":"Rahm E.","year":"2000","journal-title":"IEEE Data Engineering Bulletin"},{"key":"e_1_2_12_5_2","doi-asserted-by":"crossref","unstructured":"KoudasN. SarawagiS. andSrivastavaD. Record Linkage: Similarity Measures and Algorithms Proceedings of the 2006 ACM SIGMOD International Conference on Management of Data 2006 Chicago IL 802\u2013803.","DOI":"10.1145\/1142473.1142599"},{"key":"e_1_2_12_6_2","doi-asserted-by":"crossref","unstructured":"BilenkoM.andMooneyR. J. Adaptive Duplicate Detection Using Learnable String Similarity Measures Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2003 Washington DC 39\u201348.","DOI":"10.1145\/956750.956759"},{"key":"e_1_2_12_7_2","doi-asserted-by":"crossref","unstructured":"MudgalS. LiH. RekatsinasT.et al. Deep Learning for Entity Matching: A Design Space Exploration Proceedings of the 2018 International Conference on Management of Data 2018 Houston TX 19\u201334.","DOI":"10.1145\/3183713.3196926"},{"key":"e_1_2_12_8_2","doi-asserted-by":"crossref","unstructured":"YaoD. GuY. CongG. JinH. andLvX. Entity Resolution With Hierarchical Graph Attention Networks Proceedings of the SIGMOD\u201922: International Conference on Management of Data 2022 Philadelphia PA 429\u2013442.","DOI":"10.1145\/3514221.3517872"},{"key":"e_1_2_12_9_2","unstructured":"DouW. ShenD. ZhouX.et al. Soft Target-Enhanced Matching Framework for Deep Entity Matching Proceedings of the AAAI\u201923\/IAAI\u201923\/EAAI\u201923 2023 Washington DC."},{"key":"e_1_2_12_10_2","unstructured":"DevlinJ. ChangM. W. LeeK. andToutanovaK. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT) 2019 Minneapolis MN."},{"key":"e_1_2_12_11_2","doi-asserted-by":"publisher","DOI":"10.14778\/3467861.3467878"},{"key":"e_1_2_12_12_2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-42941-5_20","volume-title":"Using ChatGPT for Entity Matching","author":"Peeters R.","year":"2023"},{"key":"e_1_2_12_13_2","doi-asserted-by":"crossref","unstructured":"KojimaT. GuS. S. ReidM. MatsuoY. andIwasawaY. Large Language Models Are Zero-Shot Reasoners 35 Proceedings of the 36th International Conference on Neural Information Processing Systems 2022 New Orleans LA 22199\u201322213.","DOI":"10.52202\/068431-1613"},{"key":"e_1_2_12_14_2","unstructured":"XiaY. ChenJ. LiX. andGaoJ. APrompt4EM: Augmented Prompt Tuning for Generalized Entity Matching 2024 https:\/\/arxiv.org\/abs\/2405.04820."},{"key":"e_1_2_12_15_2","unstructured":"WangT. ChenX. LinH.et al. Match Compare or Select? An Investigation of Large Language Models for Entity Matching Proceedings of the 31st International Conference on Computational Linguistics Association for Computational Linguistics 2025 Abu Dhabi 96\u2013109."},{"key":"e_1_2_12_16_2","doi-asserted-by":"publisher","DOI":"10.14778\/3421424.3421431"},{"key":"e_1_2_12_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/S00778-023-00779-Z"},{"key":"e_1_2_12_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/J.KNOSYS.2022.109033"},{"key":"e_1_2_12_19_2","unstructured":"WuQ. BansalG. ZhangJ.et al. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation 2023 https:\/\/arxiv.org\/abs\/2308.08155."},{"key":"e_1_2_12_20_2","volume-title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","author":"Hong S.","year":"2024"},{"key":"e_1_2_12_21_2","doi-asserted-by":"crossref","unstructured":"DalviN. N. RastogiV. DasguptaA. SarmaA. D. andSarl\u00f3sT. Optimal Hashing Schemes for Entity Matching Proceedings of the 22nd International World Wide Web Conference 2013 Rio de Janeiro 295\u2013306.","DOI":"10.1145\/2488388.2488415"},{"key":"e_1_2_12_22_2","doi-asserted-by":"crossref","unstructured":"ElmagarmidA. K. IlyasI. F. OuzzaniM. Quian\u00e9-RuizJ. TangN. andYinS. NADEEF\/ER: Generic and Interactive Entity Resolution Proceedings of the 2014 International Conference on Management of Data 2014 Snowbird UT 1071\u20131074.","DOI":"10.1145\/2588555.2594511"},{"key":"e_1_2_12_23_2","doi-asserted-by":"publisher","DOI":"10.14778\/3149193.3149199"},{"key":"e_1_2_12_24_2","doi-asserted-by":"publisher","DOI":"10.14778\/2021017.2021020"},{"key":"e_1_2_12_25_2","doi-asserted-by":"crossref","unstructured":"CohenW. W.andRichmanJ. Learning to Match and Cluster Large High-Dimensional Data Sets for Data Integration Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2002 Edmonton 475\u2013480.","DOI":"10.1145\/775047.775116"},{"key":"e_1_2_12_26_2","doi-asserted-by":"crossref","unstructured":"GokhaleC. DasS. DoanA.et al. Corleone: Hands-Off Crowdsourcing for Entity Matching Proceedings of the 2014 International Conference on Management of Data 2014 Snowbird UT 601\u2013612.","DOI":"10.1145\/2588555.2588576"},{"key":"e_1_2_12_27_2","doi-asserted-by":"publisher","DOI":"10.14778\/3007263.3007314"},{"key":"e_1_2_12_28_2","doi-asserted-by":"publisher","DOI":"10.14778\/3236187.3236198"},{"key":"e_1_2_12_29_2","doi-asserted-by":"crossref","unstructured":"FuC. HanX. SunL.et al. End-to-End Multi-Perspective Matching for Entity Resolution Proceedings of the 28th International Joint Conference on Artificial Intelligence 2019 Macao 4961\u20134967.","DOI":"10.24963\/ijcai.2019\/689"},{"key":"e_1_2_12_30_2","doi-asserted-by":"crossref","unstructured":"KasaiJ. QianK. GurajadaS. LiY. andPopaL. Low-Resource Deep Entity Resolution With Transfer and Active Learning Proceedings of the 57th Conference of the Association for Computational Linguistics 2019 Florence 5851\u20135861.","DOI":"10.18653\/v1\/P19-1586"},{"key":"e_1_2_12_31_2","doi-asserted-by":"crossref","unstructured":"CappuzzoR. PapottiP. andThirumuruganathanS. Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks Proceedings of the 2020 International Conference on Management of Data 2020 Portland OR 1335\u20131349.","DOI":"10.1145\/3318464.3389742"},{"key":"e_1_2_12_32_2","doi-asserted-by":"crossref","unstructured":"SteinerA. PeetersR. andBizerC. Fine-Tuning Large Language Models for Entity Matching Proceedings of the 2025 IEEE 41st International Conference on Data Engineering Workshops (ICDEW) 2025 Hong Kong.","DOI":"10.1109\/ICDEW67478.2025.00006"},{"key":"e_1_2_12_33_2","unstructured":"ZhangH. DongY. XiaoC. andOyamadaM. Jellyfish: A Large Language Model for Data Preprocessing 2023 https:\/\/arxiv.org\/abs\/2312.01678."},{"key":"e_1_2_12_34_2","volume-title":"GraphER: Token-Centric Entity Resolution With Graph Convolutional Neural Networks","author":"Li B.","year":"2020"},{"key":"e_1_2_12_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3134806"},{"key":"e_1_2_12_36_2","doi-asserted-by":"crossref","unstructured":"ParkJ. S. O\u2019BrienJ. C. CaiC. J. MorrisM. R. LiangP. andBernsteinM. S. Generative Agents: Interactive Simulacra of Human Behavior 2 Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology 2023 San Francisco CA 1\u20132.","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_2_12_37_2","unstructured":"OpenAI GPT-4 Technical Report 2023 https:\/\/arxiv.org\/abs\/2303.08774."},{"key":"e_1_2_12_38_2","unstructured":"DeepSeek-Ai GuoD. YangD.et al. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 2025 https:\/\/arxiv.org\/abs\/2501.12948."},{"key":"e_1_2_12_39_2","unstructured":"DubeyA. JauhriA. PandeyA.et al. The Llama 3 Herd of Models 2024 https:\/\/arxiv.org\/abs\/2407.21783."},{"key":"e_1_2_12_40_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888900008122"},{"key":"e_1_2_12_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/S11704-024-40231-1"},{"key":"e_1_2_12_42_2","unstructured":"FerragM. A. TihanyiN. andDebbahM. From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review 2025 https:\/\/arxiv.org\/abs\/2504.19678."},{"key":"e_1_2_12_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/J.NEUNET.2025.107200"},{"key":"e_1_2_12_44_2","unstructured":"WeiJ. WangX. SchuurmansD.et al. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Proceedings of the 2022 Annual Conference on Neural Information Processing Systems 2022 New Orleans LA."},{"key":"e_1_2_12_45_2","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models","author":"Yao S.","year":"2023"},{"key":"e_1_2_12_46_2","unstructured":"LiuY. OttM. GoyalN.et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach 2019 https:\/\/arxiv.org\/abs\/1907.11692."},{"key":"e_1_2_12_47_2","unstructured":"SanhV. DebutL. ChaumondJ. andWolfT. DistilBERT A Distilled Version of BERT: Smaller Faster Cheaper and Lighter 2019 https:\/\/arxiv.org\/abs\/1910.01108."},{"key":"e_1_2_12_48_2","doi-asserted-by":"crossref","unstructured":"WarnerB. ChaffinA. Clavi\u00e9B.et al. Smarter Better Faster Longer: a Modern Bidirectional Encoder for Fast Memory Efficient and Long Context Finetuning and Inference Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics 2025 Vienna 2526\u20132547.","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"e_1_2_12_49_2","doi-asserted-by":"crossref","unstructured":"SatopaaV. AlbrechtJ. R. IrwinD. E. andRaghavanB. Finding a \u201cKneedle\u201d in a Haystack: Detecting Knee Points in System Behavior Proceedings of the 2011 31st International Conference on Distributed Computing Systems Workshops 2011 Minneapolis MN 166\u2013171.","DOI":"10.1109\/ICDCSW.2011.20"},{"key":"e_1_2_12_50_2","unstructured":"MikolovT. SutskeverI. ChenK. CorradoG. S. andDeanJ. Distributed Representations of Words and Phrases and Their Compositionality Proceedings of the 27th Annual Conference on Neural Information Processing Systems 2013 Lake Tahoe NV 3111\u20133119."},{"key":"e_1_2_12_51_2","doi-asserted-by":"crossref","unstructured":"PenningtonJ. SocherR. andManningC. D. Glove: Global Vectors for Word Representation Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing 2014 Doha 1532\u20131543.","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_2_12_52_2","doi-asserted-by":"publisher","DOI":"10.1162\/TACL_A_00051"},{"key":"e_1_2_12_53_2","first-page":"5998","article-title":"Attention is All You Need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_54_2","doi-asserted-by":"crossref","unstructured":"ZhangS. HuY. andBianG. Research on String Similarity Algorithm Based on Levenshtein Distance Proceedings of the 2017 IEEE 2nd Advanced Information Technology Electronic and Automation Control Conference (IAEAC) 2017 Chongqing 2247\u20132251.","DOI":"10.1109\/IAEAC.2017.8054419"},{"key":"e_1_2_12_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3405476"},{"key":"e_1_2_12_56_2","unstructured":"PeetersR. SteinerA. andBizerC. Entity Matching Using Large Language Models Proceedings 28th International Conference on Extending Database Technology EDBT 2025 2025 Barcelona 529\u2013541."},{"key":"e_1_2_12_57_2","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume":"32","author":"Paszke A.","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_58_2","unstructured":"WolfT. DebutL. SanhV.et al. HuggingFace\u2019s Transformers: State-of-the-Art Natural Language Processing 2019 https:\/\/arxiv.org\/abs\/1910.03771."},{"key":"e_1_2_12_59_2","unstructured":"KingmaD. P.andBaJ. Adam: A Method for Stochastic Optimization Proceedings of the 3rd International Conference on Learning Representations 2015 San Diego CA."}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/8100559","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/8100559","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/8100559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T08:30:30Z","timestamp":1781857830000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/8100559"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":59,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/int\/8100559"],"URL":"https:\/\/doi.org\/10.1155\/int\/8100559","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-08-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8100559"}}