{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T08:11:29Z","timestamp":1776154289589,"version":"3.50.1"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP230101122"],"award-info":[{"award-number":["DP230101122"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF1000100"],"award-info":[{"award-number":["2023YFF1000100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.neunet.2026.108701","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T17:18:39Z","timestamp":1770657519000},"page":"108701","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Learning fair representation for fine-tuning pre-trained language models"],"prefix":"10.1016","volume":"198","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0695-9443","authenticated-orcid":false,"given":"Ke","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6084-3278","authenticated-orcid":false,"given":"Yinghao","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8078-4401","authenticated-orcid":false,"given":"Hong-Yu","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2843-5738","authenticated-orcid":false,"given":"Lin","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9023-1878","authenticated-orcid":false,"given":"Jiuyong","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1618-3553","authenticated-orcid":false,"given":"Zaiwen","family":"Feng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0383-1462","authenticated-orcid":false,"given":"Debo","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108701_bib0001","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics (ACL 2020)","first-page":"5454","article-title":"Language (technology) is power: A critical survey of \u201cbias\u201d in NLP","author":"Blodgett","year":"2020"},{"issue":"6334","key":"10.1016\/j.neunet.2026.108701_bib0002","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1126\/science.aal4230","article-title":"Semantics derived automatically from language corpora contain human-like biases","volume":"356","author":"Caliskan","year":"2017","journal-title":"Science"},{"key":"10.1016\/j.neunet.2026.108701_bib0003","series-title":"Proceedings of the semeval workshop at ACL 2017","first-page":"1","article-title":"Semeval-2017 task 1: Semantic textual similarity\u2014multilingual and cross-lingual focused evaluation","author":"Cer","year":"2017"},{"key":"10.1016\/j.neunet.2026.108701_bib0004","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"10473","article-title":"Unsupervised editing for counterfactual stories","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2026.108701_bib0005","series-title":"Machine learning for causal inference","first-page":"189","article-title":"Causal inference and natural language processing","author":"Chen","year":"2023"},{"issue":"5","key":"10.1016\/j.neunet.2026.108701_bib0006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3636423","article-title":"Data-driven causal effect estimation based on graphical causal modelling: A survey","volume":"56","author":"Cheng","year":"2024","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.neunet.2026.108701_bib0007","first-page":"1","article-title":"Disentangled representation learning for causal inference with instruments","author":"Cheng","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108701_bib0008","series-title":"Proceedings of the 9th international conference on learning representations (ICLR 2021)","first-page":"1","article-title":"Fairfil: Contrastive neural debiasing method for pretrained text encoders","author":"Cheng","year":"2021"},{"key":"10.1016\/j.neunet.2026.108701_bib0009","series-title":"Proceedings of the NAACL-HLT 2019","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neunet.2026.108701_bib0010","series-title":"Proceedings of the NAACL-HLT 2019","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neunet.2026.108701_bib0011","series-title":"Proceedings of the ninth conference on computational natural language learning (coNLL-2005)","first-page":"72","article-title":"Automatically constructing a corpus of sentential paraphrases","author":"Dolan","year":"2005"},{"key":"10.1016\/j.neunet.2026.108701_bib0012","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1162\/tacl_a_00511","article-title":"Causal inference in natural language processing: estimation, prediction, interpretation and beyond","volume":"10","author":"Feder","year":"2022","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"11","key":"10.1016\/j.neunet.2026.108701_bib0013","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Communications of the ACM"},{"key":"10.1016\/j.neunet.2026.108701_bib0014","series-title":"Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"1012","article-title":"Auto-debias: Debiasing masked language models with automated biased prompts","author":"Guo","year":"2022"},{"key":"10.1016\/j.neunet.2026.108701_bib0015","series-title":"Advances in neural information processing systems 31 (neurIPS 2018)","first-page":"1","article-title":"Cola: Decentralized linear learning","author":"He","year":"2018"},{"issue":"1","key":"10.1016\/j.neunet.2026.108701_bib0016","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1146\/annurev-statistics-031017-100630","article-title":"Causal structure learning","volume":"5","author":"Heinze-Deml","year":"2018","journal-title":"Annual Review of Statistics and Its Application"},{"key":"10.1016\/j.neunet.2026.108701_bib0017","series-title":"Proceedings of advances in neural information processing systems (neurIPS 2021)","first-page":"24941","article-title":"A causal lens for controllable text generation","author":"Hu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108701_bib0018","series-title":"Proceedings of the 16th conference of the european chapter of the association for computational linguistics (EACL 2021)","first-page":"1","article-title":"Debiasing pre-trained contextualised embeddings","author":"Kaneko","year":"2021"},{"key":"10.1016\/j.neunet.2026.108701_bib0019","series-title":"Proceedings of the 37th international conference on machine learning (ICML 2019)","first-page":"3944","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019"},{"key":"10.1016\/j.neunet.2026.108701_bib0020","series-title":"Proceedings of the thirteenth international conference on the principles of knowledge representation and reasoning","first-page":"552","article-title":"The winograd schema challenge","author":"Levesque","year":"2012"},{"key":"10.1016\/j.neunet.2026.108701_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112635","article-title":"Contrastive learning for fair graph representations via counterfactual graph augmentation","volume":"305","author":"Li","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.108701_bib0022","article-title":"Supporting vision-language model few-shot inference with confounder-pruned knowledge prompt","author":"Li","year":"2025","journal-title":"Neural Networks"},{"issue":"9","key":"10.1016\/j.neunet.2026.108701_bib0023","first-page":"1","article-title":"Pre-trained language models for text generation: A survey","volume":"56","author":"Li","year":"2024","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.neunet.2026.108701_bib0024","series-title":"Findings of ACL 2022","first-page":"1","article-title":"How pre-trained language models capture factual knowledge? a causal-inspired analysis","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.108701_bib0025","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics (ACL 2020)","first-page":"1","article-title":"Towards debiasing sentence representations","author":"Liang","year":"2020"},{"issue":"9","key":"10.1016\/j.neunet.2026.108701_bib0026","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.neunet.2026.108701_bib0027","series-title":"Proceedings of the china national conference on chinese computational linguistics","first-page":"471","article-title":"A robustly optimized BERT pre-training approach with post-training","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.108701_bib0028","series-title":"Proceedings of the international conference on learning representations (ICLR 2019)","first-page":"1","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"10.1016\/j.neunet.2026.108701_bib0029","series-title":"Proceedings of the 11th international conference on learning representations (ICLR 2023)","first-page":"1","article-title":"Neuro-symbolic procedural planning with commonsense prompting","author":"Lu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108701_bib0030","series-title":"Information Theory, Inference and Learning Algorithms","author":"MacKay","year":"2003"},{"key":"10.1016\/j.neunet.2026.108701_bib0031","series-title":"Proceedings of the north american chapter of the association for computational linguistics (NAACL 2019)","first-page":"1","article-title":"Black is to criminal as caucasian is to police: detecting and removing multiclass bias in word embeddings","author":"Manzini","year":"2019"},{"key":"10.1016\/j.neunet.2026.108701_bib0032","series-title":"Proceedings of the 2019 conference of the north american chapter of the association for computational linguistics: human language technologies (NAACL-HLT 2019)","first-page":"622","article-title":"On measuring social biases in sentence encoders","author":"May","year":"2019"},{"key":"10.1016\/j.neunet.2026.108701_bib0033","series-title":"Proceedings of the 2022 annual meeting of the association for computational linguistics (ACL 2022)","first-page":"1","article-title":"An empirical survey of the effectiveness of debiasing techniques for pre-trained language models","author":"Meade","year":"2022"},{"key":"10.1016\/j.neunet.2026.108701_bib0034","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP 2020)","first-page":"1953","article-title":"Crows-pairs: A challenge dataset for measuring social biases in masked language models","author":"Nangia","year":"2020"},{"key":"10.1016\/j.neunet.2026.108701_bib0035","series-title":"Proceedings of the 60th annual meeting of the association for computational linguistics (ACL 2022)","first-page":"1","article-title":"Retrieval-guided counterfactual generation for QA","author":"Paranjape","year":"2022"},{"key":"10.1016\/j.neunet.2026.108701_bib0036","series-title":"Causality","author":"Pearl","year":"2009"},{"key":"10.1016\/j.neunet.2026.108701_bib0037","series-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)","first-page":"5434","article-title":"Counterfactual inference for text classification debiasing","author":"Qian","year":"2021"},{"key":"10.1016\/j.neunet.2026.108701_bib0038","series-title":"Machine Learning Challenges: Evaluating Predictive Uncertainty, Visual Object Classification, and Recognizing Textual Entailment","author":"Qui\u00f1onero-Candela","year":"2006"},{"issue":"1","key":"10.1016\/j.neunet.2026.108701_bib0039","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1037\/a0031903","article-title":"Reasoning about causal relationships: Inferences on causal networks","volume":"140","author":"Rottman","year":"2014","journal-title":"Psychological Bulletin"},{"key":"10.1016\/j.neunet.2026.108701_bib0040","series-title":"Proceedings of probabilistic and causal inference: The works of judea pearl","first-page":"765","article-title":"Causality for machine learning","author":"Sch\u00f6lkopf","year":"2022"},{"key":"10.1016\/j.neunet.2026.108701_bib0041","series-title":"Proceedings of the 2013 conference on empirical methods in natural language processing (EMNLP 2013)","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"Socher","year":"2013"},{"issue":"1","key":"10.1016\/j.neunet.2026.108701_bib0042","first-page":"1","article-title":"A survey on gender bias in natural language processing","volume":"1","author":"Sta\u0143czak","year":"2021","journal-title":"Journal of the ACM"},{"key":"10.1016\/j.neunet.2026.108701_bib0043","series-title":"Elements of Information Theory","author":"Thomas","year":"2006"},{"key":"10.1016\/j.neunet.2026.108701_bib0044","series-title":"Spurious Correlations","author":"Vigen","year":"2015"},{"key":"10.1016\/j.neunet.2026.108701_bib0045","series-title":"Proceedings of the international conference on learning representations (ICLR 2019)","first-page":"1","article-title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","author":"Wang","year":"2019"},{"key":"10.1016\/j.neunet.2026.108701_bib0046","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.eng.2022.04.024","article-title":"Pre-trained language models and their applications","volume":"25","author":"Wang","year":"2023","journal-title":"Engineering"},{"key":"10.1016\/j.neunet.2026.108701_bib0047","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP)","first-page":"7583","article-title":"Causal inference of script knowledge","author":"Weber","year":"2020"},{"key":"10.1016\/j.neunet.2026.108701_bib0048","unstructured":"Webster, K., Wang, X. et al. (2020). Measuring and reducing gendered correlations in pre-trained models. https:\/\/arxiv.org\/abs\/2010.06032."},{"key":"10.1016\/j.neunet.2026.108701_bib0049","series-title":"Pacific-asia conference on knowledge discovery and data mining","first-page":"471","article-title":"Disentangled representation with causal constraints for counterfactual fairness","author":"Xu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108701_bib0050","series-title":"Proceedings of the joint european conference on machine learning and knowledge discovery in databases (ECML PKDD 2019)","first-page":"727","article-title":"Pre-trained language model for biomedical question answering","author":"Yoon","year":"2019"},{"key":"10.1016\/j.neunet.2026.108701_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106781","article-title":"Disentangled contrastive learning for fair graph representations","volume":"181","author":"Zhang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108701_bib0052","first-page":"1","article-title":"Mitigating propensity bias of large language models for recommender systems","author":"Zhang","year":"2025","journal-title":"ACM Transactions on Information Systems"},{"key":"10.1016\/j.neunet.2026.108701_bib0053","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107314","article-title":"A general debiasing framework with counterfactual reasoning for multimodal public speaking anxiety detection","volume":"187","author":"Zhang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108701_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.107078","article-title":"Diccr: Double-gated intervention and confounder causal reasoning for vision-language navigation","volume":"184","author":"Zhou","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108701_bib0055","series-title":"Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"4227","article-title":"Causal-debias: Unifying debiasing in pretrained language models and fine-tuning via causal invariant learning","author":"Zhou","year":"2023"},{"key":"10.1016\/j.neunet.2026.108701_bib0056","series-title":"Proceedings of the 57th annual meeting of the association for computational linguistics (ACL 2019)","first-page":"1651","article-title":"Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology","author":"Zmigrod","year":"2019"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026001632?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026001632?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T07:38:21Z","timestamp":1776152301000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026001632"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":56,"alternative-id":["S0893608026001632"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108701","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Learning fair representation for fine-tuning pre-trained language models","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108701","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108701"}}