A Survey on Bias in Deep NLP
Open accessPublished version of a preprint
The DOI matches its Crossref record; 91 of the 91 references it cites were found in a registry or an index.
Abstract
Deep neural networks are hegemonic approaches to many machine learning areas, including natural language processing (NLP). Thanks to the availability of large corpora collections and the capability of deep architectures to shape internal language mechanisms in self-supervised learning processes (also known as “pre-training”), versatile and performing models are released continuously for every new network design. These networks, somehow, learn a probability distribution of words and relations across the training collection used, inheriting the potential flaws, inconsistencies and biases contained in such a collection. As pre-trained models have been found to be very useful approaches to transfer learning, dealing with bias has become a relevant issue in this new scenario. We introduce bias in a formal way and explore how it has been treated in several networks, in terms of detection and correction. In addition, available resources are identified and a strategy to deal with bias in deep NLP is proposed.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · 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) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Journal of personality and social psychology
Armstrong, J. S. (1988) · International Journal of Forecasting · doi:10.1016/0169-2070(88)90126-4 · Cited by 10,485
Measuring individual differences in implicit cognition: the implicit association test
Greenwald, A. G., McGhee, D. E., & Schwartz, J. L. K. (1998) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.74.6.1464 · Cited by 9,210
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137
On the psychology of prediction.
Kahneman, D., & Tversky, A. (1973) · Psychological Review · doi:10.1037/h0034747 · Cited by 6,202
Research works printed but not linked: 9
- Stubbs, M. Text and Corpus Analysis: Computer-Assisted Studies of Language and Culture; Blackwell: Oxford, UK, 1996.
- Radford, A.; Wu, J.; Child, R.; Luan, D.; Amodei, D.; Sutskever, I. Language models are unsupervised multitask learners. OpenAI Blog 2019, 1, 9.
- Gigerenzer, G. Bounded and rational. In Philosophie: Grundlagen und Anwendungen/Philosophy: Foundations and Applications; Mentis: Paderborn, Germany, 2008; pp. 233-257.
- Schneider, D.J. The Psychology of Stereotyping; Guilford Press: New York, NY, USA, 2005.
- Ziemski, M.; Junczys-Dowmunt, M.; Pouliquen, B. The United Nations Parallel Corpus v1.0. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), Portorož, Slovenia, 23-28 May 2016; pp. 3530-3534.
- Díaz Martínez, C.; Díaz García, P.; Navarro Sustaeta, P. Hidden Gender Bias in Big Data as Revealed by Neural Networks: Man is to Woman as Work is to Mother? Rev. Esp. Investig. Sociol. 2020, 172, 41-60.
- Clark, K.; Manning, C.D. Deep Reinforcement Learning for Mention-Ranking Coreference Models. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, TX, USA, 1-5 November 2016; pp. 2256-2262. [CrossRef] · DOI · Paper page
- Farkas, A.; N'emeth, R. How to Measure Gender Bias in Machine Translation: Optimal Translators, Multiple Reference Points. arXiv 2020, arXiv:2011.06445. · arXiv
- Gupta, M.; Agrawal, P. Compression of Deep Learning Models for Text: A Survey. arXiv 2020, arXiv:2008.05221. · arXiv
Cited by
Items 101–123 of 123
Case Reports Unlocked: Harnessing Large Language Models to Advance Research on Child MaltreatmentPreprint
Stoll, D., Wehrli, S., & Lätsch, D. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4928223
Putting People First: A Multimodal Bi‐Stream Structure‐based Model for Bias Mitigation
Zhou, S. F., Bu, W., Li, X., & Wang, H. (2024) · Proceedings of the Association for Information Science and Technology · doi:10.1002/pra2.1225
New Frontiers in Metaphor Visualization
Cerutti, M., Miroslw, L. M., & Polidoro, P. (2025) · Linguistic Frontiers · doi:10.2478/lf-2024-0022
Optimal word order for non-causal text generation with Large Language Models: The Spanish case
Busto-Castiñeira, A., García-Méndez, S., de Arriba-Pérez, F., & González-Castaño, F. J. (2025) · Pattern Recognition Letters · doi:10.1016/j.patrec.2025.02.010 · Cited by 3
Detecting Linguistic Bias in Government Documents Using Large language Models
de Swart, M., den Hengst, F., & Chen, J. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714526 · Cited by 5
Applications and Challenges of Fairness APIs in Machine Learning Software
Das, A., Uddin, G., Chowdhury, S., Akhond, M. R., & Hemmati, H. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3765735 · Cited by 2
Lenguaje, género y visibilidad profesional: nomina agentis en el ámbito médico en España e Italia
Alfano, I. (2025) · Revista de Investigación Lingüística · doi:10.6018/ril.657191
Concept Control for LLM Safety Using Radial Basis Function Representations
Amos, M., Song, Y., & Pagnucco, M. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4969-6_17
Ueno, T., & Inoshita, K. (2025) · IEEE Conference on Pervasive and Intelligent Computing (PICom) · doi:10.1109/picom68402.2025.00011
Kurup, A. R., Kar, M. K., Dev, S., & Neog, D. R. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.113857
Girard, W., Xu, H., & Yan, D. (2026) · Sensors · doi:10.3390/s26020676
Gosztonyi, M. (2026) · Sexuality & Culture · doi:10.1007/s12119-026-10580-z
Modeling automated legal and ethical compliance for trustworthy AI
Taheri, Y. (2024) · theses.fr (ABES) · doi:10.70675/5971a37cz548bz4673z8186z5e4e8ed8cf1b · Cited by 1
How to (Un)Link the Bias: Linked Data to Counteract Dataset Bias
Cimitan, A., Alves-Pinto, A., & Geierhos, M. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-25308-8_8
Comparative Analysis of Deep Learning Architectures for Bias-Aware Toxicity Classification
Gayathre, V., Sruthi, B., Sucheta, P., Baskar, V., A, Y. J., Gopika, V., & Kirubavathi, G. (2026) · International Conference on Recent Advancement in Electrical, Computer and Communication Technologies (IECCT) · doi:10.1109/iecct68664.2026.11541760
Proxy Analysis in Bias Testing
Djennane, L., Kardkovács, Z. T., Benatallah, B., Gaci, Y., & Farah, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-28117-3_15
Expert Consensus on LLM Safety in Clinical Decision Support
Gayathri, K. V., Kanshiya, S., Saranraj, P., Lokeshwari, B., Vilmasen, P., & Wins, J. A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7862-6.ch011
Stoll, D., Perron, B. E., Qi, Z., Steinmann, S., Eicher, N. F., & Jud, A. (2026) · Research on Social Work Practice · doi:10.1177/10497315261446932
Quantifying Social Biases in Language Model Classifiers is Domain-Dependent
Quiroga, T., Bravo-Márquez, F., & Barrière, V. (2026) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3834859
Bias and Representation Analysis in Indian Code-Mixed NLP Datasets: A Multi-Dataset Study
Arunkumar, G., & Deepa, M. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-31523-6_4
Explainable AI for Clinical Oncology Decisions
Dey, N., Misra, B., Fong, S., Sherratt, R. S., & Shi, F. (2026) · International Conference on Intelligent Engineering and Next-Gen Healthcare Systems (IEHNS) · doi:10.1109/iehns68708.2026.11606796
Continuous Mitigation of Intersectional Algorithmic Pink Tax via PCA-Driven Latent Space Projection
Wang, T., & Sun, P. (2026) · International Conference on Machine Learning and Intelligent Computing · doi:10.1145/3829441.3829623
StereoSet-PT: The Stereotype Evaluation Framework for Brazilian Portuguese Language Models
Aleixo, D. S., Costa, R. P., Pellicer, L. F. A. O., & de Almeida, R. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39882-6_46
Metadata
- Authors
- Garrido-Muñoz, I., Montejo-Ráez, A., Martínez-Santiago, F., & Ureña-López, L. A.
- Affiliations
- Universidad de Jaén (ES)
- Centro de Estudios Avanzados en TIC (CEATIC), 230071 Jaén, Spain
- Corresponding author
- Garrido-Muñoz, Ismael
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2021-04-02
- Volume
- 11
- Issue
- 7
- Pages
- 3184
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W3134678353
- Cited by
- 123
- References
- 74
- Citations by year
- 2026: 14 · 2025: 25 · 2024: 27 · 2023: 28 · 2022: 15 · 2021: 14
- FWCI
- 26.29
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- Preprints.org (acceptedVersion, cc-by)
- RUJA (Universidad de Jaén) (publishedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Spanish Government (RTI2018-094653-B-C21)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- algorithmic bias, pre-trained language models, transfer learning, bias detection, bias correction, training data bias, bias mitigation strategies
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
