{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T04:08:12Z","timestamp":1751342892511,"version":"3.41.0"},"reference-count":92,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front. Comput. Sci."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s11704-025-41143-4","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T11:17:38Z","timestamp":1751282258000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards uncertainty-calibrated structural data enrichment with large language model for few-shot entity resolution"],"prefix":"10.1007","volume":"19","author":[{"given":"Mengyi","family":"Yan","sequence":"first","affiliation":[]},{"given":"Yaoshu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiaohan","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Haoyi","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Jianxin","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"41143_CR1","unstructured":"Liu Y. RoBERTa: a robustly optimized BERT pretraining approach. 2019, arXiv preprint arXiv: 1907.11692"},{"issue":"1","key":"41143_CR2","doi-asserted-by":"publisher","first-page":"50","DOI":"10.14778\/3421424.3421431","volume":"14","author":"Y Li","year":"2020","unstructured":"Li Y, Li J, Suhara Y, Doan A, Tan W C. Deep entity matching with pretrained language models. Proceedings of the VLDB Endowment, 2020, 14(1): 50\u201360","journal-title":"Proceedings of the VLDB Endowment"},{"key":"41143_CR3","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1145\/3448016.3457258","volume-title":"Proceedings of 2021 International Conference on Management of Data","author":"Z Miao","year":"2021","unstructured":"Miao Z, Li Y, Wang X. Rotom: a meta-learned data augmentation framework for entity matching, data cleaning, text classification, and beyond. In: Proceedings of 2021 International Conference on Management of Data. 2021, 1303\u20131316"},{"issue":"2","key":"41143_CR4","doi-asserted-by":"publisher","first-page":"369","DOI":"10.14778\/3565816.3565836","volume":"16","author":"P Wang","year":"2022","unstructured":"Wang P, Zeng X, Chen L, Ye F, Mao Y, Zhu J, Gao Y. PromptEM: prompt-tuning for low-resource generalized entity matching. Proceedings of the VLDB Endowment, 2022, 16(2): 369\u2013378","journal-title":"Proceedings of the VLDB Endowment"},{"key":"41143_CR5","first-page":"3982","volume-title":"Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing","author":"N Reimers","year":"2019","unstructured":"Reimers N, Gurevych I. Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 2019, 3982\u20133992"},{"key":"41143_CR6","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1145\/3183713.3196926","volume-title":"Proceedings of 2018 International Conference on Management of Data","author":"S Mudgal","year":"2018","unstructured":"Mudgal S, Li H, Rekatsinas T, Doan A, Park Y, Krishnan G, Deep R, Arcaute E, Raghavendra V. Deep learning for entity matching: a design space exploration. In: Proceedings of 2018 International Conference on Management of Data. 2018, 19\u201334"},{"key":"41143_CR7","doi-asserted-by":"publisher","first-page":"4633","DOI":"10.1145\/3459637.3482008","volume-title":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","author":"J Wang","year":"2021","unstructured":"Wang J, Li Y, Hirota W. Machamp: a generalized entity matching benchmark. In: Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 2021, 4633\u20134642"},{"key":"41143_CR8","unstructured":"Chaudhury S, Dan S, Das P, Kollias G, Nelson E. Needle in the haystack for memory based large language models. 2024, arXiv preprint arXiv: 2407.01437"},{"key":"41143_CR9","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/978-981-97-5569-1_20","volume-title":"Proceedings of the 29th International Conference on Database Systems for Advanced Applications","author":"J Tang","year":"2024","unstructured":"Tang J, Dou W, Shen D, Nie T, Kou Y. Towards long-text entity resolution with chain-of-thought knowledge augmentation from large language models. In: Proceedings of the 29th International Conference on Database Systems for Advanced Applications. 2024, 322\u2013336"},{"key":"41143_CR10","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.1145\/3318464.3389743","volume-title":"Proceedings of 2020 ACM SIGMOD International Conference on Management of Data","author":"R Wu","year":"2020","unstructured":"Wu R, Chaba S, Sawlani S, Chu X, Thirumuruganathan S. ZeroER: entity resolution using zero labeled examples. In: Proceedings of 2020 ACM SIGMOD International Conference on Management of Data. 2020, 1149\u20131164"},{"key":"41143_CR11","first-page":"13628","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics","author":"J He","year":"2024","unstructured":"He J, Pan K, Dong X, Song Z, LiuYiBo L, Qianguosun Q, Liang Y, Wang H, Zhang E, Zhang J. Never lost in the middle: mastering long-context question answering with position-agnostic decompositional training. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024, 13628\u201313642"},{"key":"41143_CR12","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1162\/tacl_a_00638","volume":"12","author":"N F Liu","year":"2024","unstructured":"Liu N F, Lin K, Hewitt J, Paranjape A, Bevilacqua M, Petroni F, Liang P. Lost in the middle: how language models use long contexts. Transactions of the Association for Computational Linguistics, 2024, 12: 157\u2013173","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"6","key":"41143_CR13","doi-asserted-by":"publisher","first-page":"186357","DOI":"10.1007\/s11704-024-40555-y","volume":"18","author":"D Xu","year":"2024","unstructured":"Xu D, Chen W, Peng W, Zhang C, Xu T, Zhao X, Wu X, Zheng Y, Wang Y, Chen E. Large language models for generative information extraction: a survey. Frontiers of Computer Science, 2024, 18(6): 186357","journal-title":"Frontiers of Computer Science"},{"key":"41143_CR14","unstructured":"Singh I S, Aggarwal R, Allahverdiyev I, Taha M, Akalin A, Zhu K, O\u2019Brien S. ChunkRAG: novel LLM-chunk filtering method for rag systems. 2024, arXiv preprint arXiv: 2410.19572"},{"key":"41143_CR15","doi-asserted-by":"publisher","first-page":"8754","DOI":"10.18653\/v1\/2024.emnlp-main.497","volume-title":"Proceedings of 2024 Conference on Empirical Methods in Natural Language Processing","author":"H Zhang","year":"2024","unstructured":"Zhang H, Dong Y, Xiao C, Oyamada M. Jellyfish: instruction-tuning local large language models for data preprocessing. In: Proceedings of 2024 Conference on Empirical Methods in Natural Language Processing. 2024, 8754\u20138782"},{"issue":"4","key":"41143_CR16","doi-asserted-by":"publisher","first-page":"738","DOI":"10.14778\/3574245.3574258","volume":"16","author":"A Narayan","year":"2022","unstructured":"Narayan A, Chami I, Orr L, R\u00e9 C. Can foundation models wrangle your data? Proceedings of the VLDB Endowment, 2022, 16(4): 738\u2013746","journal-title":"Proceedings of the VLDB Endowment"},{"key":"41143_CR17","first-page":"65","volume":"18","author":"C Cardie","year":"1997","unstructured":"Cardie C. Empirical methods in information extraction. AI Magazine, 1997, 18(4): 65\u201379","journal-title":"AI Magazine"},{"key":"41143_CR18","unstructured":"Wu H, Yuan Y, Mikaelyan L, Meulemans A, Liu X, Hensman J, Mitra B. Structured entity extraction using large language models. 2024, arXiv preprint arXiv: 2402.04437"},{"key":"41143_CR19","doi-asserted-by":"publisher","first-page":"184318","DOI":"10.1007\/s11704-023-2639-2","volume":"18","author":"Y Yang","year":"2024","unstructured":"Yang Y, Huang P, Cao J, Li J, Lin Y, Ma F. A prompt-based approach to adversarial example generation and robustness enhancement. Frontiers of Computer Science, 2024, 18(4): 184318","journal-title":"Frontiers of Computer Science"},{"issue":"5","key":"41143_CR20","doi-asserted-by":"publisher","first-page":"185347","DOI":"10.1007\/s11704-024-40013-9","volume":"18","author":"Y Wu","year":"2024","unstructured":"Wu Y, Yang X. A glance at in-context learning. Frontiers of Computer Science, 2024, 18(5): 185347","journal-title":"Frontiers of Computer Science"},{"issue":"2","key":"41143_CR21","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1145\/3703155","volume":"43","author":"L Huang","year":"2025","unstructured":"Huang L, Yu W, Ma W, Zhong W, Feng Z, Wang H, Chen Q, Peng W, Feng X, Qin B, Liu T. A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems, 2025, 43(2): 42","journal-title":"ACM Transactions on Information Systems"},{"issue":"2","key":"41143_CR22","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/3377455","volume":"53","author":"G Papadakis","year":"2021","unstructured":"Papadakis G, Skoutas D, Thanos E, Palpanas T. Blocking and filtering techniques for entity resolution: a survey. ACM Computing Surveys, 2021, 53(2): 31","journal-title":"ACM Computing Surveys"},{"issue":"1","key":"41143_CR23","doi-asserted-by":"publisher","first-page":"407","DOI":"10.14778\/1687627.1687674","volume":"2","author":"W Fan","year":"2009","unstructured":"Fan W, Jia X, Li J, Ma S. Reasoning about record matching rules. Proceedings of the VLDB Endowment, 2009, 2(1): 407\u2013418","journal-title":"Proceedings of the VLDB Endowment"},{"key":"41143_CR24","unstructured":"Kejriwal M, Miranker D P. A DNF blocking scheme learner for heterogeneous datasets. 2015, arXiv preprint arXiv: 1501.01694"},{"issue":"8","key":"41143_CR25","doi-asserted-by":"publisher","first-page":"1946","DOI":"10.1109\/TKDE.2013.54","volume":"26","author":"G Papadakis","year":"2014","unstructured":"Papadakis G, Koutrika G, Palpanas T, Nejdl W. Meta-blocking: taking entity resolutionto the next level. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(8): 1946\u20131960","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"2","key":"41143_CR26","doi-asserted-by":"publisher","first-page":"189","DOI":"10.14778\/3149193.3149199","volume":"11","author":"R Singh","year":"2017","unstructured":"Singh R, Meduri V V, Elmagarmid A, Madden S, Papotti P, Quian\u00e9-Ruiz J A, Solar-Lezama A, Tang N. Synthesizing entity matching rules by examples. Proceedings of the VLDB Endowment, 2017, 11(2): 189\u2013202","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"6","key":"41143_CR27","doi-asserted-by":"publisher","first-page":"1507","DOI":"10.14778\/3583140.3583163","volume":"16","author":"D Paulsen","year":"2023","unstructured":"Paulsen D, Govind Y, Doan A. Sparkly: a simple yet surprisingly strong TF\/IDF blocker for entity matching. Proceedings of the VLDB Endowment, 2023, 16(6): 1507\u20131519","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"3","key":"41143_CR28","doi-asserted-by":"publisher","first-page":"278","DOI":"10.14778\/3291264.3291272","volume":"12","author":"G C Paul Suganthan","year":"2018","unstructured":"Paul Suganthan G C, Ardalan A, Doan A, Akella A. Smurf: self-service string matching using random forests. Proceedings of the VLDB Endowment, 2018, 12(3): 278\u2013291","journal-title":"Proceedings of the VLDB Endowment"},{"key":"41143_CR29","first-page":"411","volume-title":"Proceedings of 2015 IEEE International Conference on Big Data (Big Data)","author":"V Efthymiou","year":"2015","unstructured":"Efthymiou V, Papadakis G, Papastefanatos G, Stefanidis K, Palpanas T. Parallel meta-blocking: realizing scalable entity resolution over large, heterogeneous data. In: Proceedings of 2015 IEEE International Conference on Big Data (Big Data). 2015, 411\u2013420"},{"issue":"11","key":"41143_CR30","doi-asserted-by":"publisher","first-page":"2459","DOI":"10.14778\/3476249.3476294","volume":"14","author":"S Thirumuruganathan","year":"2021","unstructured":"Thirumuruganathan S, Li H, Tang N, Ouzzani M, Govind Y, Paulsen D, Fung G, Doan A. Deep learning for blocking in entity matching: a design space exploration. Proceedings of the VLDB Endowment, 2021, 14(11): 2459\u20132472","journal-title":"Proceedings of the VLDB Endowment"},{"key":"41143_CR31","first-page":"1502","volume-title":"Proceedings of the 39th IEEE International Conference on Data Engineering","author":"R Wang","year":"2023","unstructured":"Wang R, Li Y, Wang J. Sudowoodo: contrastive self-supervised learning for multi-purpose data integration and preparation. In: Proceedings of the 39th IEEE International Conference on Data Engineering. 2023, 1502\u20131515"},{"key":"41143_CR32","first-page":"121","volume-title":"Proceedings of the 21st International Conference on the Semantic Web","author":"A Brinkmann","year":"2024","unstructured":"Brinkmann A, Shraga R, Bizer C. SC-block: supervised contrastive blocking within entity resolution pipelines. In: Proceedings of the 21st International Conference on the Semantic Web. 2024, 121\u2013142"},{"issue":"3","key":"41143_CR33","doi-asserted-by":"publisher","first-page":"292","DOI":"10.14778\/3632093.3632096","volume":"17","author":"S Wu","year":"2023","unstructured":"Wu S, Wu Q, Dong H, Hua W, Zhou X. Blocker and matcher can mutually benefit: a co-learning framework for low-resource entity resolution. Proceedings of the VLDB Endowment, 2023, 17(3): 292\u2013304","journal-title":"Proceedings of the VLDB Endowment"},{"key":"41143_CR34","unstructured":"Wang T, Lin H, Han X, Chen X, Cao B, Sun L. Towards universal dense blocking for entity resolution. 2024, arXiv preprint arXiv: 2404.14831"},{"issue":"1\u20132","key":"41143_CR35","doi-asserted-by":"publisher","first-page":"417","DOI":"10.14778\/1920841.1920897","volume":"3","author":"S Guo","year":"2010","unstructured":"Guo S, Dong X L, Srivastava D, Zajac R. Record linkage with uniqueness constraints and erroneous values. Proceedings of the VLDB Endowment, 2010, 3(1\u20132): 417\u2013428","journal-title":"Proceedings of the VLDB Endowment"},{"key":"41143_CR36","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s00778-010-0206-6","volume":"20","author":"W Fan","year":"2011","unstructured":"Fan W, Gao H, Jia X, Li J, Ma S. Dynamic constraints for record matching. The VLDB Journal, 2011, 20(4): 495\u2013520","journal-title":"The VLDB Journal"},{"issue":"6","key":"41143_CR37","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1007\/s00778-013-0308-z","volume":"22","author":"S E Whang","year":"2013","unstructured":"Whang S E, Garcia-Molina H. Joint entity resolution on multiple datasets. The VLDB Journal, 2013, 22(6): 773\u2013795","journal-title":"The VLDB Journal"},{"issue":"12","key":"41143_CR38","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.14778\/2994509.2994535","volume":"9","author":"P Konda","year":"2016","unstructured":"Konda P, Das S, Paul Suganthan G C, Doan A, Ardalan A, Ballard J R, Li H, Panahi F, Zhang H, Naughton J, Prasad S, Krishnan G, Deep R, Raghavendra V. Magellan: toward building entity matching management systems. Proceedings of the VLDB Endowment, 2016, 9(12): 1197\u20131208","journal-title":"Proceedings of the VLDB Endowment"},{"issue":"11","key":"41143_CR39","doi-asserted-by":"publisher","first-page":"1454","DOI":"10.14778\/3236187.3236198","volume":"11","author":"M Ebraheem","year":"2018","unstructured":"Ebraheem M, Thirumuruganathan S, Joty S, Ouzzani M, Tang N. Distributed representations of tuples for entity resolution. Proceedings of the VLDB Endowment, 2018, 11(11): 1454\u20131467","journal-title":"Proceedings of the VLDB Endowment"},{"key":"41143_CR40","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1145\/3308558.3313578","volume-title":"Proceedings of the World Wide Web Conference","author":"C Zhao","year":"2019","unstructured":"Zhao C, He Y. Auto-EM: end-to-end fuzzy entity-matching using pretrained deep models and transfer learning. In: Proceedings of the World Wide Web Conference. 2019, 2413\u20132424"},{"key":"41143_CR41","first-page":"8172","volume-title":"Proceedings of the 34th AAAI Conference on Artificial Intelligence","author":"B Li","year":"2020","unstructured":"Li B, Wang W, Sun Y, Zhang L, Ali M A, Wang Y. GraphER: token-centric entity resolution with graph convolutional neural networks. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence. 2020, 8172\u20138179"},{"key":"41143_CR42","first-page":"4961","volume-title":"Proceedings of the 28th International Joint Conference on Artificial Intelligence","author":"C Fu","year":"2019","unstructured":"Fu C, Han X, Sun L, Chen B, Zhang W, Wu S, Kong H. End-to-end multi-perspective matching for entity resolution. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence. 2019, 4961\u20134967"},{"key":"41143_CR43","doi-asserted-by":"publisher","first-page":"184319","DOI":"10.1007\/s11704-023-2542-x","volume":"18","author":"J Tang","year":"2024","unstructured":"Tang J, Song R, Huang Y, Gao S, Yu Z. Semantic-aware entity alignment for low resource language knowledge graph. Frontiers of Computer Science, 2024, 18(4): 184319","journal-title":"Frontiers of Computer Science"},{"key":"41143_CR44","first-page":"3421","volume-title":"Proceedings of the 40th IEEE International Conference on Data Engineering","author":"X Zeng","year":"2024","unstructured":"Zeng X, Wang P, Mao Y, Chen L, Liu X, Gao Y. MultiEM: efficient and effective unsupervised multi-table entity matching. In: Proceedings of the 40th IEEE International Conference on Data Engineering. 2024, 3421\u20133434"},{"key":"41143_CR45","first-page":"118","volume-title":"Proceedings of the 25th International Conference on Extending Database Technology","author":"N Kirielle","year":"2022","unstructured":"Kirielle N, Christen P, Ranbaduge T. TransER: homogeneous transfer learning for entity resolution. In: Proceedings of the 25th International Conference on Extending Database Technology. 2022, 118\u2013130"},{"issue":"12","key":"41143_CR46","doi-asserted-by":"publisher","first-page":"3666","DOI":"10.14778\/3554821.3554870","volume":"15","author":"J Tu","year":"2022","unstructured":"Tu J, Han X, Fan J, Tang N, Chai C, Li G, Du X. DADER: hands-off entity resolution with domain adaptation. Proceedings of the VLDB Endowment, 2022, 15(12): 3666\u20133669","journal-title":"Proceedings of the VLDB Endowment"},{"key":"41143_CR47","doi-asserted-by":"publisher","first-page":"1975","DOI":"10.1145\/3589334.3645397","volume-title":"Proceedings of the ACM Web Conference 2024","author":"C Sun","year":"2024","unstructured":"Sun C, Xu Y, Shen D, Nie T. Matching feature separation network for domain adaptation in entity matching. In: Proceedings of the ACM Web Conference 2024. 2024, 1975\u20131985"},{"issue":"1","key":"41143_CR48","first-page":"2","volume":"13","author":"M Loster","year":"2021","unstructured":"Loster M, Koumarelas I, Naumann F. Knowledge transfer for entity resolution with Siamese neural networks. Journal of Data and Information Quality (JDIQ), 2021, 13(1): 2","journal-title":"Journal of Data and Information Quality (JDIQ)"},{"issue":"1","key":"41143_CR49","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1145\/3665252.3665263","volume":"53","author":"J Fan","year":"2024","unstructured":"Fan J, Tu J, Li G, Wang P, Du X, Jia X, Gao S, Tang N. Unicorn: a unified multi-tasking matching model. ACM SIGMOD Record, 2024, 53(1): 44\u201353","journal-title":"ACM SIGMOD Record"},{"key":"41143_CR50","first-page":"13226","volume-title":"Proceedings of the 35th AAAI Conference on Artificial Intelligence","author":"B Li","year":"2021","unstructured":"Li B, Miao Y, Wang Y, Sun Y, Wang W. Improving the efficiency and effectiveness for BERT-based entity resolution. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence. 2021, 13226\u201313233"},{"issue":"3","key":"41143_CR51","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1145\/3654979","volume":"2","author":"P Li","year":"2024","unstructured":"Li P, He Y, Yashar D, Cui W, Ge S, Zhang H, Rifinski Fainman D, Zhang D, Chaudhuri S. Table-GPT: table fine-tuned GPT for diverse table tasks. Proceedings of the ACM on Management of Data, 2024, 2(3): 176","journal-title":"Proceedings of the ACM on Management of Data"},{"key":"41143_CR52","first-page":"96","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"T Wang","year":"2025","unstructured":"Wang T, Chen X, Lin H, Chen X, Han X, Sun L, Wang H, Zeng Z. Match, compare, or select? An investigation of large language models for entity matching. In: Proceedings of the 31st International Conference on Computational Linguistics. 2025, 96\u2013109"},{"key":"41143_CR53","doi-asserted-by":"crossref","unstructured":"Li H, Feng L, Li S, Hao F, Zhang C J, Song Y, Chen L. On leveraging large language models for enhancing entity resolution: a cost-efficient approach. 2024, arXiv preprint arXiv: 2401.03426","DOI":"10.1145\/3589335.3651245"},{"issue":"S1","key":"41143_CR54","doi-asserted-by":"publisher","first-page":"1513","DOI":"10.1007\/s10462-023-10562-9","volume":"56","author":"J Gawlikowski","year":"2023","unstructured":"Gawlikowski J, Tassi C R N, Ali M, Lee J, Humt M, Feng J, Kruspe A, Triebel R, Jung P, Roscher R, Shahzad M, Yang W, Bamler R, Zhu X X. A survey of uncertainty in deep neural networks. Artificial Intelligence Review, 2023, 56(S1): 1513\u20131589","journal-title":"Artificial Intelligence Review"},{"key":"41143_CR55","first-page":"5580","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"A Kendall","year":"2017","unstructured":"Kendall A, Gal Y. What uncertainties do we need in Bayesian deep learning for computer vision? In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 5580\u20135590"},{"key":"41143_CR56","unstructured":"Kadavath S, Conerly T, Askell A, Henighan T, Drain D, et al. Language models (mostly) know what they know. 2022, arXiv preprint arXiv: 2207.05221"},{"key":"41143_CR57","first-page":"1076","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"X Zhao","year":"2020","unstructured":"Zhao X, Chen F, Hu S, Cho J H. Uncertainty aware semi-supervised learning on graph data. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 1076"},{"issue":"3","key":"41143_CR58","doi-asserted-by":"publisher","first-page":"183311","DOI":"10.1007\/s11704-023-2427-z","volume":"18","author":"Q Liu","year":"2024","unstructured":"Liu Q, Zhang Q, Zhao F, Wang G. Uncertain knowledge graph embedding: an effective method combining multi-relation and multi-path. Frontiers of Computer Science, 2024, 18(3): 183311","journal-title":"Frontiers of Computer Science"},{"key":"41143_CR59","first-page":"159","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"T B Brown","year":"2020","unstructured":"Brown T B, Mann B, Ryder N, Subbiah M, Kaplan J D, et al. Language models are few-shot learners. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 159"},{"key":"41143_CR60","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M A, Lacroix T, Rozi\u00e8re B, Goyal N, Hambro E, Azhar F, Rodriguez A, Joulin A, Grave E, Lample G. LLaMA: open and efficient foundation language models. 2023, arXiv preprint arXiv: 2302.13971"},{"key":"41143_CR61","unstructured":"Jiang A Q, Sablayrolles A, Mensch A, Bamford C, Chaplot D S, de las Casas D, Bressand F, Lengyel G, Lample G, Saulnier L, Lavaud L R, Lachaux M A, Stock P, Scao T L, Lavril T, Wang T, Lacroix T, Sayed W E. Mistral 7B. 2023, arXiv preprint arXiv: 2310.06825"},{"key":"41143_CR62","doi-asserted-by":"publisher","first-page":"7273","DOI":"10.18653\/v1\/2022.findings-emnlp.538","volume-title":"Proceedings of Findings of the Association for Computational Linguistics: EMNLP 2022","author":"Y Xiao","year":"2022","unstructured":"Xiao Y, Liang P P, Bhatt U, Neiswanger W, Salakhutdinov R, Morency L P. Uncertainty quantification with pre-trained language models: a large-scale empirical analysis. In: Proceedings of Findings of the Association for Computational Linguistics: EMNLP 2022. 2022, 7273\u20137284"},{"key":"41143_CR63","unstructured":"Lin S, Hilton J, Evans O. Teaching models to express their uncertainty in words. Transactions on Machine Learning Research, 2022"},{"key":"41143_CR64","doi-asserted-by":"publisher","first-page":"9004","DOI":"10.18653\/v1\/2023.emnlp-main.557","volume-title":"Proceedings of 2023 Conference on Empirical Methods in Natural Language Processing","author":"P Manakul","year":"2023","unstructured":"Manakul P, Liusie A, Gales M. SelfCheckGPT: zero-resource black-box hallucination detection for generative large language models. In: Proceedings of 2023 Conference on Empirical Methods in Natural Language Processing. 2023, 9004\u20139017"},{"key":"41143_CR65","volume-title":"Proceedings of the 9th International Conference on Learning Representations","author":"A Malinin","year":"2021","unstructured":"Malinin A, Gales M. Uncertainty estimation in autoregressive structured prediction. In: Proceedings of the 9th International Conference on Learning Representations. 2021"},{"issue":"10","key":"41143_CR66","doi-asserted-by":"publisher","first-page":"1910352","DOI":"10.1007\/s11704-024-3983-6","volume":"19","author":"M Li","year":"2025","unstructured":"Li M, Shi X, Qiao C, Huang X, Wang W, Wan Y, Zhang T, Jin H. E2CNN: entity-type-enriched cascaded neural network for Chinese financial relation extraction. Frontiers of Computer Science, 2025, 19(10): 1910352","journal-title":"Frontiers of Computer Science"},{"issue":"2","key":"41143_CR67","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1109\/TSE.2024.3519464","volume":"51","author":"Y Huang","year":"2025","unstructured":"Huang Y, Song J, Wang Z, Zhao S, Chen H, Juefei-Xu F, Ma L. Look before you leap: an exploratory study of uncertainty analysis for large language models. IEEE Transactions on Software Engineering, 2025, 51(2): 413\u2013429","journal-title":"IEEE Transactions on Software Engineering"},{"key":"41143_CR68","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"L Kuhn","year":"2023","unstructured":"Kuhn L, Gal Y, Farquhar S. Semantic uncertainty: linguistic invariances for uncertainty estimation in natural language generation. In: Proceedings of the 11th International Conference on Learning Representations. 2023"},{"key":"41143_CR69","first-page":"5050","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics","author":"J Duan","year":"2024","unstructured":"Duan J, Cheng H, Wang S, Zavalny A, Wang C, Xu R, Kailkhura B, Xu K. Shifting attention to relevance: towards the predictive uncertainty quantification of free-form large language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024, 5050\u20135063"},{"key":"41143_CR70","doi-asserted-by":"publisher","first-page":"8653","DOI":"10.18653\/v1\/2023.findings-acl.551","volume-title":"Proceedings of Findings of the Association for Computational Linguistics: ACL 2023","author":"Z Yin","year":"2023","unstructured":"Yin Z, Sun Q, Guo Q, Wu J, Qiu X, Huang X J. Do large language models know what they don\u2019t know? In: Proceedings of Findings of the Association for Computational Linguistics: ACL 2023. 2023, 8653\u20138665"},{"key":"41143_CR71","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1145\/3616855.3635752","volume-title":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","author":"Y Sui","year":"2024","unstructured":"Sui Y, Zhou M, Zhou M, Han S, Zhang D. Table meets LLM: can large language models understand structured table data? A benchmark and empirical study. In: Proceedings of the 17th ACM International Conference on Web Search and Data Mining. 2024, 645\u2013654"},{"key":"41143_CR72","unstructured":"Krell M M, Kosec M, P\u00e9rez S P, Fitzgibbon A. Efficient sequence packing without cross-contamination: accelerating large language models without impacting performance. 2022, arXiv preprint arXiv: 2107.02027"},{"key":"41143_CR73","doi-asserted-by":"crossref","unstructured":"Luo K, Liu Z, Xiao S, Liu K. BGE landmark embedding: a chunking-free embedding method for retrieval augmented long-context large language models. 2024, arXiv preprint arXiv: 2402.11573","DOI":"10.18653\/v1\/2024.acl-long.180"},{"key":"41143_CR74","volume-title":"Llamaindex","author":"J Liu","year":"2023","unstructured":"Liu J. Llamaindex. See GitHub repository (LlamaIndex) website, 2023"},{"key":"41143_CR75","first-page":"1597","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"T Chen","year":"2020","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G. A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 1597\u20131607"},{"key":"41143_CR76","volume-title":"Wiley StatsRef: Statistics Reference Online","author":"D Kornbrot","year":"2014","unstructured":"Kornbrot D. Point biserial correlation. In: Wiley StatsRef: Statistics Reference Online. New York: John Wiley & Sons, 2014"},{"key":"41143_CR77","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-031-78090-5_4","volume-title":"Proceedings of the 26th International Conference on Information Integration and Web Intelligence","author":"A Brinkmann","year":"2025","unstructured":"Brinkmann A, Shraga R, Bizer C. ExtractGPT: exploring the potential of large language models for product attribute value extraction. In: Proceedings of the 26th International Conference on Information Integration and Web Intelligence. 2025, 38\u201352"},{"key":"41143_CR78","unstructured":"Dong Y, Ruan C F, Cai Y, Lai R, Xu Z, Zhao Y, Chen T. XGrammar: flexible and efficient structured generation engine for large language models. 2024, arXiv preprint arXiv: 2411.15100"},{"key":"41143_CR79","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1145\/3600006.3613165","volume-title":"Proceedings of the 29th Symposium on Operating Systems Principles","author":"W Kwon","year":"2023","unstructured":"Kwon W, Li Z, Zhuang S, Sheng Y, Zheng L, Yu C H, Gonzalez J, Zhang H, Stoica I. Efficient memory management for large language model serving with PagedAttention. In: Proceedings of the 29th Symposium on Operating Systems Principles. 2023, 611\u2013626"},{"issue":"8017","key":"41143_CR80","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s41586-024-07421-0","volume":"630","author":"S Farquhar","year":"2024","unstructured":"Farquhar S, Kossen J, Kuhn L, Gal Y. Detecting hallucinations in large language models using semantic entropy. Nature, 2024, 630(8017): 625\u2013630","journal-title":"Nature"},{"key":"41143_CR81","first-page":"19274","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Y Leviathan","year":"2023","unstructured":"Leviathan Y, Kalman M, Matias Y. Fast inference from transformers via speculative decoding. In: Proceedings of the 40th International Conference on Machine Learning. 2023, 19274\u201319286"},{"key":"41143_CR82","doi-asserted-by":"publisher","first-page":"446","DOI":"10.18653\/v1\/2023.emnlp-demo.41","volume-title":"Proceedings of 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"E Fadeeva","year":"2023","unstructured":"Fadeeva E, Vashurin R, Tsvigun A, Vazhentsev A, Petrakov S, Fedyanin K, Vasilev D, Goncharova E, Panchenko A, Panov M, Baldwin T, Shelmanov A. LM-polygraph: uncertainty estimation for language models. In: Proceedings of 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2023, 446\u2013461"},{"issue":"3","key":"41143_CR83","doi-asserted-by":"publisher","first-page":"183338","DOI":"10.1007\/s11704-023-3355-7","volume":"18","author":"J Zhang","year":"2024","unstructured":"Zhang J, Fan R, Tao H, Jiang J, Hou C. Constrained clustering with weak label prior. Frontiers of Computer Science, 2024, 18(3): 183338","journal-title":"Frontiers of Computer Science"},{"key":"41143_CR84","doi-asserted-by":"publisher","first-page":"400","DOI":"10.18653\/v1\/2024.acl-demos.38","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","author":"Y Zheng","year":"2024","unstructured":"Zheng Y, Zhang R, Zhang J, Ye Y, Luo Z, Feng Z, Ma Y. Llamafactory: unified efficient fine-tuning of 100+ language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). 2024, 400\u2013410"},{"key":"41143_CR85","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/3308560.3316609","volume-title":"Proceedings of the 2019 World Wide Web Conference","author":"A Primpeli","year":"2019","unstructured":"Primpeli A, Peeters R, Bizer C. The WDC training dataset and gold standard for large-scale product matching. In: Proceedings of the 2019 World Wide Web Conference. 2019, 381\u2013386"},{"key":"41143_CR86","volume-title":"Proceedings of the 9th International Conference on Learning Representations","author":"P He","year":"2021","unstructured":"He P, Liu X, Gao J, Chen W. DeBERTa: decoding-enhanced BERT with disentangled attention. In: Proceedings of the 9th International Conference on Learning Representations. 2021"},{"key":"41143_CR87","unstructured":"Zhang P, Xiao S, Liu Z, Dou Z, Nie J Y. Retrieve anything to augment large language models. 2023, arXiv preprint arXiv: 2310.07554"},{"key":"41143_CR88","doi-asserted-by":"publisher","first-page":"17716","DOI":"10.18653\/v1\/2024.emnlp-main.981","volume-title":"Proceedings of 2024 Conference on Empirical Methods in Natural Language Processing","author":"X Wang","year":"2024","unstructured":"Wang X, Wang Z, Gao X, Zhang F, Wu Y, Xu Z, Shi T, Wang Z, Li S, Qian Q, Yin R, Lv C, Zheng X, Huang X. Searching for best practices in retrieval-augmented generation. In: Proceedings of 2024 Conference on Empirical Methods in Natural Language Processing. 2024, 17716\u201317736"},{"key":"41143_CR89","volume-title":"spaCy: industrial-strength natural language processing in python","author":"M Honnibal","year":"2020","unstructured":"Honnibal M, Montani I, Van Landeghem S, Boyd A. spaCy: industrial-strength natural language processing in python. See github.com\/explosion\/spaCy website, 2020"},{"issue":"1","key":"41143_CR90","first-page":"140","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu P J. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 2020, 21(1): 140","journal-title":"The Journal of Machine Learning Research"},{"issue":"10","key":"41143_CR91","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","volume":"57","author":"D Vrande\u010di\u0107","year":"2014","unstructured":"Vrande\u010di\u0107 D, Kr\u00f6tzsch M. Wikidata: a free collaborative knowledgebase. Communications of the ACM, 2014, 57(10): 78\u201385","journal-title":"Communications of the ACM"},{"issue":"11","key":"41143_CR92","doi-asserted-by":"publisher","first-page":"3109","DOI":"10.14778\/3681954.3681987","volume":"17","author":"M Yan","year":"2024","unstructured":"Yan M, Fan W, Wang Y, Xie M. Enriching relations with additional attributes for ER. Proceedings of the VLDB Endowment, 2024, 17(11): 3109\u20133123","journal-title":"Proceedings of the VLDB Endowment"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-025-41143-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-025-41143-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-025-41143-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T12:03:29Z","timestamp":1751285009000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-025-41143-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":92,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["41143"],"URL":"https:\/\/doi.org\/10.1007\/s11704-025-41143-4","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"24 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"1911376"}}