{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T16:29:46Z","timestamp":1787588986658,"version":"build-2736575974"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007835","name":"Silesian University of Technology","doi-asserted-by":"publisher","award":["09\/010\/RGJ24\/0031"],"award-info":[{"award-number":["09\/010\/RGJ24\/0031"]}],"id":[{"id":"10.13039\/501100007835","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009392","name":"Prince Sattam bin Abdulaziz University","doi-asserted-by":"publisher","award":["PSAU\/2023\/R\/1445"],"award-info":[{"award-number":["PSAU\/2023\/R\/1445"]}],"id":[{"id":"10.13039\/100009392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3360306","type":"journal-article","created":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T18:49:47Z","timestamp":1706640587000},"page":"26183-26195","source":"Crossref","is-referenced-by-count":30,"title":["Shortcut Learning Explanations for Deep Natural Language Processing: A Survey on Dataset Biases"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3870-5068","authenticated-orcid":false,"given":"Varun","family":"Dogra","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Lovely Professional University, Phagwara, Punjab, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3136-4029","authenticated-orcid":false,"given":"Sahil","family":"Verma","sequence":"additional","affiliation":[{"name":"Uttaranchal University, Dehradun, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5422-1659","authenticated-orcid":false,"family":"Kavita","sequence":"additional","affiliation":[{"name":"Uttaranchal University, Dehradun, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9073-5347","authenticated-orcid":false,"given":"Marcin","family":"Wo\u017aniak","sequence":"additional","affiliation":[{"name":"Faculty of Applied Mathematics, Silesian University of Technology, Gliwice, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6859-670X","authenticated-orcid":false,"given":"Jana","family":"Shafi","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering and Information, College of Engineering in Wadi Alddawasir, Prince Sattam Bin Abdulaziz University, Wadi Alddawasir, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5206-272X","authenticated-orcid":false,"given":"Muhammad Fazal","family":"Ijaz","sequence":"additional","affiliation":[{"name":"School of IT and Engineering, Melbourne Institute of Technology, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neur. Inf. Process. Sys.","volume":"33","author":"Brown"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1459"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.aal4230"},{"key":"ref6","article-title":"The measure and mismeasure of fairness","author":"Corbett-Davies","year":"2018","journal-title":"arXiv:1808.00023"},{"key":"ref7","article-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping","author":"Dodge","year":"2019","journal-title":"arXiv:2002.06305"},{"issue":"240","key":"ref8","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","article-title":"Rethinking softmax cross-entropy loss for adversarial robustness","author":"Pang","year":"2019","journal-title":"arXiv:1905.10626"},{"key":"ref10","first-page":"642","article-title":"UniLMv2: Pseudo-masked language models for unified language model pre-training","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Bao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-022-01455-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1302"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S18-2005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3596490"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3194770.3194776"},{"key":"ref17","first-page":"1","article-title":"Man is to computer programmer as woman is to homemaker? Debiasing word embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bolukbasi"},{"key":"ref18","first-page":"19000","article-title":"The origins and prevalence of texture bias in convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Hermann"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(79)90023-4"},{"key":"ref20","article-title":"On formalizing fairness in prediction with machine learning","author":"Gajane","year":"2017","journal-title":"arXiv:1710.03184"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/s18-1185"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.71"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143889"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/math9243319"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref27","first-page":"1","article-title":"Linear Hinge loss and average margin","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"11","author":"Gentile"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1341"},{"key":"ref29","article-title":"The statistics of word cooccurrences word pairs and collocations","author":"Evert","year":"2005"},{"key":"ref30","article-title":"Why do masked neural language models still need common sense knowledge?","author":"Kwon","year":"2019","journal-title":"arXiv:1911.03024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1215"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.341"},{"key":"ref33","first-page":"78","article-title":"Analyzing biases to spurious correlations in text classification tasks","volume-title":"Proc. 2nd Conf. Asia\u2013Pacific Chapter Association Comput. Linguistics, 12th Int. Joint Conf. Natural Lang. Process.","volume":"2","author":"Liusie"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/systems10060233"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2307\/jj.5232958"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/n15-1098"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2123"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1070"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1334"},{"issue":"2","key":"ref43","first-page":"1298","article-title":"PAWS: Paraphrase adversaries from word scrambling","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguist. Human Lang. Technol.","volume":"1","author":"Zhang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-2103"},{"key":"ref45","first-page":"12907","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1061"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-6115"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.755"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1316"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016867"},{"key":"ref53","first-page":"2340","article-title":"Stress test evaluation for natural language inference","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Naik"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.773"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.122"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.23"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-4453-6_2"},{"key":"ref58","article-title":"Quantifying and reducing stereotypes in word embeddings","author":"Bolukbasi","year":"2016","journal-title":"arXiv:1606.06121"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ARSO.2017.8025197"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-017-1116-3"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052660"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1166"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1062"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1720347115"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1162"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462536"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1159"},{"key":"ref68","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xie"},{"key":"ref69","article-title":"Domain adaptation for neural machine translation","author":"Saunders","year":"2021"},{"key":"ref70","first-page":"962","article-title":"Fairness constraints: Mechanisms for fair classification","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","volume":"54","author":"Zafar"},{"key":"ref71","first-page":"6565","article-title":"Towards understanding and mitigating social biases in language models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Liang"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1111\/lnc3.12432"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.7"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-62077-6_14"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00240"},{"key":"ref77","first-page":"1668","article-title":"The risk of racial bias in hate speech detection","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Card"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1121"},{"key":"ref79","article-title":"Mitigating socioeconomic bias in language models","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Daum\u00e9"},{"key":"ref80","article-title":"FairPy: A toolkit for evaluation of social biases and their mitigation in large language models","author":"Viswanath","year":"2023","journal-title":"arXiv:2302.05508"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00550"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2090"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22747-0_7"},{"key":"ref85","article-title":"Mitigating bias in natural language processing models: Interventions and implications","volume-title":"Proc. Conf. Fairness, Accountability, Transparency (FAccT)","author":"Dixon"},{"key":"ref86","article-title":"Explaining and mitigating shortcut learning in transformer language models","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics (NAACL)","author":"Jain"},{"key":"ref87","article-title":"Towards a comprehensive understanding of shortcut learning in deep neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10416838.pdf?arnumber=10416838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:54:14Z","timestamp":1725252854000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10416838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3360306","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}