{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T06:40:23Z","timestamp":1767595223352,"version":"3.48.0"},"reference-count":78,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Large pre-trained language models have become a crucial backbone for many downstream tasks in natural language processing (NLP), and while they are trained on a plethora of data containing a variety of biases, such as gender biases, it has been shown that they can also inherit such biases in their weights, potentially affecting their prediction behavior. However, it is unclear to what extent these biases also affect feature attributions generated by applying \u201cexplainable artificial intelligence\u201d (XAI) techniques, possibly in unfavorable ways. To systematically study this question, we create a gender-controlled text dataset, GECO, in which the alteration of grammatical gender forms induces class-specific words and provides ground truth feature attributions for gender classification tasks. This enables an objective evaluation of the correctness of XAI methods. We apply this dataset to the pre-trained BERT model, which we fine-tune to different degrees, to quantitatively measure how pre-training induces undesirable bias in feature attributions and to what extent fine-tuning can mitigate such explanation bias. To this extent, we provide GECOBench, a rigorous quantitative evaluation framework for benchmarking popular XAI methods. We show a clear dependency between explanation performance and the number of fine-tuned layers, where XAI methods are observed to benefit particularly from fine-tuning or complete retraining of embedding layers.<\/jats:p>","DOI":"10.3389\/frai.2025.1694388","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T06:38:19Z","timestamp":1767595099000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GECOBench: a gender-controlled text dataset and benchmark for quantifying biases in explanations"],"prefix":"10.3389","volume":"8","author":[{"given":"Rick","family":"Wilming","sequence":"first","affiliation":[]},{"given":"Artur","family":"Dox","sequence":"additional","affiliation":[]},{"given":"Hjalmar","family":"Schulz","sequence":"additional","affiliation":[]},{"given":"Marta","family":"Oliveira","sequence":"additional","affiliation":[]},{"given":"Benedict","family":"Clark","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Haufe","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2026,1,5]]},"reference":[{"key":"B1","article-title":"\u201cOpenXAI: towards a transparent evaluation of model explanations,\u201d","author":"Agarwal","year":"2022","journal-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track"},{"key":"B2","doi-asserted-by":"publisher","first-page":"533","DOI":"10.18653\/v1\/2021.emnlp-main.42","article-title":"\u201cMitigating language-dependent ethnic bias in BERT,\u201d","author":"Ahn","year":"2021","journal-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Online and Punta Cana, Dominican Republic"},{"key":"B3","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.inffus.2021.11.008","article-title":"CLEVR-XAI: a benchmark dataset for the ground truth evaluation of neural network explanations","volume":"81","author":"Arras","year":"2022","journal-title":"Inf. Fusion"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1194","DOI":"10.1145\/3531146.3533179","article-title":"\u201cThe road to explainability is paved with bias: measuring the fairness of explanations,\u201d","author":"Balagopalan","year":"2022"},{"key":"B5","first-page":"313","article-title":"\u201cMechanisms of linguistic bias: how words reflect and maintain stereotypic expectancies,\u201d","author":"Beukeboom","year":"2014","journal-title":"Social Cognition and Communication"},{"key":"B6","doi-asserted-by":"publisher","first-page":"5454","DOI":"10.18653\/v1\/2020.acl-main.485","article-title":"\u201cLanguage (technology) is power: a critical survey of \u201cbias\u201d","author":"Blodgett","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"},{"key":"B7","first-page":"4356","article-title":"\u201cMan is to computer programmer as woman is to homemaker? Debiasing word embeddings,\u201d","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS'16","author":"Bolukbasi","year":"2016"},{"key":"B8","doi-asserted-by":"publisher","first-page":"7","DOI":"10.18653\/v1\/N19-3002","article-title":"\u201cIdentifying and reducing gender bias in word-level language models,\u201d","author":"Bordia","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop"},{"key":"B9","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1162\/tacl_a_00408","article-title":"Multimodal pretraining unmasked: a meta-analysis and a unified framework of vision-and-language BERTs","volume":"9","author":"Bugliarello","year":"2021","journal-title":"Trans. Assoc. Comput. Linguist"},{"key":"B10","doi-asserted-by":"publisher","first-page":"8465","DOI":"10.18653\/v1\/2023.emnlp-main.525","article-title":"\u201cEvaluating bias and fairness in gender-neutral pretrained vision-and-language models,\u201d","author":"Cabello","year":"2023","journal-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.16234","article-title":"True to the model or true to the data?","author":"Chen","year":"2020","journal-title":"arXiv [preprint]"},{"key":"B12","first-page":"4238","article-title":"\u201cCuration of benchmark templates for measuring gender bias in named entity recognition models,\u201d","author":"Cimitan","year":"2024","journal-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)"},{"key":"B13","doi-asserted-by":"publisher","first-page":"101794","DOI":"10.1016\/j.measen.2024.101794","article-title":"EXACT: towards a platform for empirically benchmarking machine learning model explanation methods","volume":"38","author":"Clark","year":"2025","journal-title":"Meas. Sens"},{"key":"B14","doi-asserted-by":"publisher","first-page":"6871","DOI":"10.1007\/s10994-024-06574-3","article-title":"XAI-TRIS: non-linear image benchmarks to quantify false positive post-hoc attribution of feature importance","volume":"113","author":"Clark","year":"2024","journal-title":"Mach. Learn"},{"key":"B15","first-page":"4081","article-title":"\u201cGeBioToolkit: automatic extraction of gender-balanced multilingual corpus of wikipedia biographies,\u201d","author":"Costa-juss\u00e0","year":"2020","journal-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference"},{"key":"B16","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1145\/3514094.3534159","article-title":"\u201cFairness via explanation quality: evaluating disparities in the quality of post hoc explanations,\u201d","volume-title":"Proceedings of the 2022 AAAI\/ACM Conference on AI, Ethics, and Society","author":"Dai","year":"2022"},{"key":"B17","doi-asserted-by":"publisher","first-page":"100101","DOI":"10.1016\/j.dim.2025.100101","article-title":"Evaluating explainability in language classification models: a unified framework incorporating feature attribution methods and key factors affecting faithfulness","volume":"9","author":"Dehdarirad","year":"2025","journal-title":"Data Inf. Manag"},{"key":"B18","doi-asserted-by":"publisher","first-page":"7659","DOI":"10.1609\/aaai.v34i05.6267","article-title":"On measuring and mitigating biased inferences of word embeddings","volume":"34","author":"Dev","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B19","first-page":"2","article-title":"\u201cBert: pre-training of deep bidirectional transformers for language understanding,\u201d","volume-title":"Proceedings of Naacl-HLT, Vol. 1","author":"Devlin","year":"2019"},{"key":"B20","doi-asserted-by":"publisher","first-page":"4443","DOI":"10.18653\/v1\/2020.acl-main.408","article-title":"\u201cERASER: a benchmark to evaluate rationalized NLP models,\u201d","author":"DeYoung","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2002.06305","article-title":"Fine-tuning pretrained language models: weight initializations, data orders, and early stopping","author":"Dodge","year":"2020","journal-title":"arXiv [preprint]"},{"key":"B22","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1198\/000313005X41337","article-title":"Graphical views of suppression and multicollinearity in multiple linear regression","volume":"59","author":"Friedman","year":"2005","journal-title":"Am. Stat"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2007.06011","article-title":"Explaining the data or explaining a model? Shapley values that uncover non-linear dependencies","author":"Fryer","year":"2020","journal-title":"arXiv [preprint]"},{"key":"B24","first-page":"296","article-title":"\u201cA novel interpretability metric for explaining bias in language models: applications on multilingual models from Southeast Asia,\u201d","author":"Gamboa","year":"2024","journal-title":"Proceedings of the 38th Pacific Asia Conference on Language, Information and Computation"},{"key":"B25","doi-asserted-by":"publisher","first-page":"154290","DOI":"10.1109\/ACCESS.2019.2946594","article-title":"Target-dependent sentiment classification with bert","volume":"7","author":"Gao","year":"2019","journal-title":"IEEE Access"},{"key":"B26","first-page":"609","article-title":"\u201cLipstick on a pig: debiasing methods cover up systematic gender biases in word embeddings but do not remove them,\u201d","author":"Gonen","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)"},{"key":"B27","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1145\/2700171.2791036","article-title":"\u201cFirst women, second sex: gender bias in Wikipedia,\u201d","volume-title":"Proceedings of the 26th ACM Conference on Hypertext & Social Media","author":"Graells-Garrido","year":"2015"},{"key":"B28","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.neuroimage.2013.10.067","article-title":"On the interpretation of weight vectors of linear models in multivariate neuroimaging","volume":"87","author":"Haufe","year":"2014","journal-title":"NeuroImage"},{"key":"B29","article-title":"\u201cPosition: XAI needs formal notions of explanation correctness,\u201d","author":"Haufe","year":"2024","journal-title":"Interpretable AI: Past, Present and Future"},{"key":"B30","article-title":"\u201cA benchmark for interpretability methods in deep neural networks,\u201d","volume-title":"Advances in Neural Information Processing Systems, Vol. 32","author":"Hooker","year":"2019"},{"key":"B31","first-page":"6441","article-title":"Benchmarking deep learning interpretability in time series predictions","volume":"33","author":"Ismail","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B32","article-title":"\u201cInput-cell attention reduces vanishing saliency of recurrent neural networks,\u201d","volume-title":"Advances in Neural Information Processing Systems, Vol. 32","author":"Ismail","year":"2019"},{"key":"B33","doi-asserted-by":"crossref","first-page":"4198","DOI":"10.18653\/v1\/2020.acl-main.386","article-title":"\u201cTowards faithfully interpretable NLP systems: how should we define and evaluate faithfulness?\u201d","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Jacovi","year":"2020"},{"key":"B34","doi-asserted-by":"publisher","first-page":"184","DOI":"10.18653\/v1\/2022.gebnlp-1.20","article-title":"\u201cGender bias in BERT - measuring and analysing biases through sentiment rating in a realistic downstream classification task,\u201d","author":"Jentzsch","year":"2022"},{"key":"B35","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1038\/s42256-020-00236-4","article-title":"Drug discovery with explainable artificial intelligence","volume":"2","author":"Jim\u00e9nez-Luna","year":"2020","journal-title":"Nat. Mach. Intell"},{"key":"B36","doi-asserted-by":"publisher","first-page":"126851","DOI":"10.1016\/j.neucom.2023.126851","article-title":"Saliency guided debiasing: detecting and mitigating biases in LMs using feature attribution","volume":"563","author":"Joshi","year":"2024","journal-title":"Neurocomputing"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.12434","article-title":"Learning the difference that makes a difference with counterfactually-augmented data","author":"Kaushik","year":"2019","journal-title":"arXiv [preprint]"},{"key":"B38","first-page":"2668","article-title":"\u201cInterpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV),\u201d","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2018"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2009.07896","article-title":"Captum: a unified and generic model interpretability library for PyTorch","author":"Kokhlikyan","year":"2020","journal-title":"arXiv [preprint]"},{"key":"B40","doi-asserted-by":"publisher","first-page":"187","DOI":"10.18653\/v1\/2021.naacl-main.18","article-title":"\u201cCounterfactual data augmentation for neural machine translation,\u201d","author":"Liu","year":"2021","journal-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.11692","article-title":"RoBERTa: a robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv [preprint]"},{"key":"B42","first-page":"4765","article-title":"\u201cA unified approach to interpreting model predictions,\u201d","author":"Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30"},{"key":"B43","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery","volume":"2","author":"Lundberg","year":"2018","journal-title":"Nat. Biomed. Eng"},{"key":"B44","doi-asserted-by":"publisher","first-page":"615","DOI":"10.18653\/v1\/N19-1062","article-title":"\u201cBlack is to criminal as caucasian is to police: detecting and removing multiclass bias in word embeddings,\u201d","author":"Manzini","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)"},{"key":"B45","doi-asserted-by":"crossref","first-page":"2374","DOI":"10.1145\/3630106.3659043","article-title":"\u201cUnderstanding disparities in post hoc machine learning explanation,\u201d","volume-title":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","author":"Mhasawade","year":"2024"},{"key":"B46","article-title":"\u201cThe need for biases in learning generalizations,\u201d","author":"Mitchell","year":"2007","journal-title":"Rutgers CS tech report, CBM-TR-117"},{"key":"B47","first-page":"277","article-title":"\u201cThe futility of bias-free learning and search,\u201d","volume-title":"Australasian Joint Conference on Artificial Intelligence","author":"Monta\u01f9ez","year":"2019"},{"key":"B48","doi-asserted-by":"publisher","first-page":"22071","DOI":"10.1073\/pnas.1900654116","article-title":"Definitions, methods, and applications in interpretable machine learning","volume":"116","author":"Murdoch","year":"2019","journal-title":"Proc. Nat. Acad. Sci"},{"key":"B49","doi-asserted-by":"publisher","first-page":"5356","DOI":"10.18653\/v1\/2021.acl-long.416","article-title":"\u201cStereoSet: measuring stereotypical bias in pretrained language models,\u201d","author":"Nadeem","year":"2021","journal-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)"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1953","DOI":"10.18653\/v1\/2020.emnlp-main.154","article-title":"\u201cCrowS-pairs: a challenge dataset for measuring social biases in masked language models,\u201d","author":"Nangia","year":"2020","journal-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"B51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3597307","article-title":"Biases in large language models: origins, inventory, and discussion","volume":"15","author":"Navigli","year":"2023","journal-title":"J. Data Inf. Qual"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1330919","DOI":"10.3389\/frai.2024.1330919","article-title":"Benchmarking the influence of pre-training on explanation performance in MR image classification","volume":"7","author":"Oliveira","year":"2024","journal-title":"Front. Artif. Intell"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.08774","article-title":"GPT-4 technical report","year":"2023","journal-title":"arXiv [preprint]"},{"key":"B54","doi-asserted-by":"publisher","first-page":"2086","DOI":"10.18653\/v1\/2022.findings-acl.165","article-title":"\u201cBBQ: a hand-built bias benchmark for question answering,\u201d","author":"Parrish","year":"2022","journal-title":"Findings of the Association for Computational Linguistics: ACL 2022"},{"key":"B55","doi-asserted-by":"publisher","first-page":"69","DOI":"10.18653\/v1\/W19-3810","article-title":"\u201cDebiasing embeddings for reduced gender bias in text classification,\u201d","author":"Prost","year":"2019","journal-title":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing"},{"key":"B56","author":"Radford","year":"2018","journal-title":"Improving Language Understanding by Generative Pre-training"},{"key":"B57","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"B58","first-page":"21","article-title":"Gender bias in wikipedia and britannica","volume":"5","author":"Reagle","year":"2011","journal-title":"Int. J. Commun"},{"key":"B59","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.18653\/v1\/N16-3020","author":"Ribeiro","year":"2016"},{"key":"B60","first-page":"18770","article-title":"\u201cA consistent and efficient evaluation strategy for attribution methods,\u201d","author":"Rong","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning, Vol. 162"},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2012.13190","article-title":"QUACKIE: a NLP classification task with ground truth explanations","author":"Rychener","year":"2020","journal-title":"arXiv [preprint]"},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6","author":"Samek","year":"2019","journal-title":"Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, volume 11700 of Lecture Notes in Computer Science"},{"key":"B63","first-page":"3145","article-title":"\u201cLearning important features through propagating activation differences,\u201d","author":"Shrikumar","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6034","article-title":"Deep inside convolutional networks: visualising image classification models and saliency maps","author":"Simonyan","year":"2013","journal-title":"arXiv [preprint]"},{"key":"B65","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1108\/eb026526","article-title":"A statistical interpretation of term specificity and its application in retrieval","volume":"28","author":"Sparck Jones","year":"1972","journal-title":"J. Doc"},{"key":"B66","article-title":"\u201cStriving for simplicity: the all convolutional net,\u201d","author":"Springenberg","year":"2015","journal-title":"ICLR (Workshop Track)"},{"key":"B67","doi-asserted-by":"crossref","first-page":"1714","DOI":"10.1145\/3630106.3658999","article-title":"\u201cSIDEs: separating idealization from deceptive \u201cexplanations' in xAI,\u201d","volume-title":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","author":"Sullivan","year":"2024"},{"key":"B68","first-page":"3319","article-title":"\u201cAxiomatic attribution for deep networks,\u201d","author":"Sundararajan","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning, Volume 70 of Proceedings of Machine Learning Research"},{"key":"B69","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1109\/TAI.2022.3228834","article-title":"Quantifying explainability of saliency methods in deep neural networks with a synthetic dataset","volume":"4","author":"Tjoa","year":"2023","journal-title":"IEEE Trans. Artif. Intell"},{"key":"B70","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1186\/s13073-021-00968-x","article-title":"Deep learning in cancer diagnosis, prognosis and treatment selection","volume":"13","author":"Tran","year":"2021","journal-title":"Genome Med"},{"key":"B71","doi-asserted-by":"publisher","first-page":"1903","DOI":"10.1007\/s10994-022-06167-y","article-title":"Scrutinizing xai using linear ground-truth data with suppressor variables","volume":"111","author":"Wilming","year":"2022","journal-title":"Mach. Learn"},{"key":"B72","first-page":"37091","article-title":"\u201cTheoretical behavior of XAI methods in the presence of suppressor variables,\u201d","author":"Wilming","year":"2023","journal-title":"Proceedings of the 40th International Conference on Machine Learning, Volume 202 of Proceedings of Machine Learning Research"},{"key":"B73","article-title":"\u201cXLNet: generalized autoregressive pretraining for language understanding,\u201d","volume-title":"Advances in Neural Information Processing Systems, Vol. 32","author":"Yang","year":"2019"},{"key":"B74","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/751","article-title":"\u201cAdapting bert for target-oriented multimodal sentiment classification,\u201d","author":"Yu","year":"2019","journal-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"},{"key":"B75","doi-asserted-by":"publisher","first-page":"1897","DOI":"10.18653\/v1\/2023.findings-emnlp.127","article-title":"\u201cDiFair: a benchmark for disentangled assessment of gender knowledge and bias,\u201d","author":"Zakizadeh","year":"2023","journal-title":"Findings of the Association for Computational Linguistics: EMNLP 2023"},{"key":"B76","doi-asserted-by":"publisher","first-page":"237","DOI":"10.3390\/diagnostics12020237","article-title":"Applications of explainable artificial intelligence in diagnosis and surgery","volume":"12","author":"Zhang","year":"2022","journal-title":"Diagnostics"},{"key":"B77","doi-asserted-by":"publisher","first-page":"2979","DOI":"10.18653\/v1\/D17-1323","article-title":"\u201cMen also like shopping: reducing gender bias amplification using corpus-level constraints,\u201d","author":"Zhao","year":"2017","journal-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing"},{"key":"B78","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1007\/978-3-030-36204-1_37","article-title":"\u201cA new method of improving bert for text classification,\u201d","volume-title":"Intelligence Science and Big Data Engineering. Big Data and Machine Learning: 9th International Conference, IScIDE 2019, Nanjing, China, October 17-20, 2019, Proceedings, Part II 9","author":"Zheng","year":"2019"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1694388\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T06:38:26Z","timestamp":1767595106000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1694388\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":78,"alternative-id":["10.3389\/frai.2025.1694388"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1694388","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,5]]},"article-number":"1694388"}}