Measuring and Mitigating Gender Bias in Legal Contextualized Language Models
Open accessThe DOI matches its Crossref record; 97 of the 98 references it cites were found in a registry or an index.
Abstract
Transformer-based contextualized language models constitute the state-of-the-art in several natural language processing (NLP) tasks and applications. Despite their utility, contextualized models can contain human-like social biases, as their training corpora generally consist of human-generated text. Evaluating and removing social biases in NLP models has been a major research endeavor. In parallel, NLP approaches in the legal domain, namely, legal NLP or computational law, have also been increasing. Eliminating unwanted bias in legal NLP is crucial, since the law has the utmost importance and effect on people. In this work, we focus on the gender bias encoded in BERT-based models. We propose a new template-based bias measurement method with a new bias evaluation corpus using crime words from the FBI database. This method quantifies the gender bias present in BERT-based models for legal applications. Furthermore, we propose a new fine-tuning-based debiasing method using the European Court of Human Rights (ECtHR) corpus to debias legal pre-trained models. We test the debiased models’ language understanding performance on the LexGLUE benchmark to confirm that the underlying semantic vector space is not perturbed during the debiasing process. Finally, we propose a bias penalty for the performance scores to emphasize the effect of gender bias on model performance.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Notably, there is growing attention on assessing LLM bias [63-64] and robustness [323-324].”
From A Survey of Large Language Models (2026) · cites this paper as [64]
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
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
Advances in neural information processing systems 7
Cios, K., & Shields, M. (1997) · Neurocomputing · doi:10.1016/s0925-2312(97)90018-7 · Cited by 22,059
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
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
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019) · arXiv · doi:10.48550/arxiv.1910.01108 · Cited by 4,653
Research works printed but not linked: 9
- [5] Kevin D. Ashley. 1988. Modelling Legal Argument: Reasoning with Cases and Hypotheticals . Ph. D. Dissertation. University of Massachusetts. -
- [16] Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, and Adam Kalai. 2016. Man is to computer programmer as woman is to homemaker? Debiasing word embeddings. In Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS'16) . Curran Associates Inc., Red Hook, NY, 435-364. -
- [26] Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis, and Ion Androutsopoulos. 2019. Neural contract element extraction revisited. In Proceedings of the Workshop on Document Intelligence at NeurIPS . Retrieved from https://openreview.net/forum?id=B1x6fa95UH -
- [36] Filippo Galgani, Paul Compton, and Achim Hoffmann. 2012. Combining different summarization techniques for legal text. In Proceedings of the Workshop on Innovative Hybrid Approaches to the Processing of Textual Data (HYBRID'12) . Association for Computational Linguistics, 115-123. -
- [50] [Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: Alite BERT for self-supervised learning of language representations. In Proceedings of the 8th International Conference on Learning Representations (ICLR'20) . OpenReview.net, 17 pages. Retrieved from https://openreview.net/forum?id= H1eA7AEtvS](https://openreview.net/forum?id=H1eA7AEtvS) -
- [64] Conor O'Sullivan and Joeran Beel. 2019. Predicting the outcome of judicial decisions made by the European Court of Human Rights. In Proceedings of the 27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science . -
- [67] Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog 1, 8 (2019), 9 . -
- [78] [Don Tuggener, Pius von Däniken, Thomas Peetz, and Mark Cieliebak. 2020. LEDGAR: A large-scale multi-label corpus for text classification of legal provisions in contracts. In Proceedings of the 12th Language Resources and Evaluation Conference . European Language Resources Association, 1235-1241. Retrieved from https://aclanthology.org/2020.lrec1.155](https://aclanthology.org/2020.lrec-1.155) -
- [87] Manzil Zaheer, Guru Guruganesh, Kumar Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, and Amr Ahmed. 2020. Big Bird: Transformers for longer sequences. In Advances in Neural Information Processing Systems , H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 17283-17297. Retrieved from https://proceedings.neurips.cc/paper/2020/file/ c8512d142a2d849725f31a9a7a361ab9-Paper.pdf -
Cited by
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
Sociodemographic biases in medical decision making by large language models
Omar, M., Soffer, S., Agbareia, R., Bragazzi, N. L., Apakama, D. U., Horowitz, C. R., Charney, A. W., Freeman, R., Kummer, B., Glicksberg, B. S., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03626-6 · Cited by 173
“Our findings align with earlier reports identifying gender biases in LLM-based clinical recommendations 20,35,36 .”
Omar, M., Sorin, V., Agbareia, R., Apakama, D. U., Soroush, A., Sakhuja, A., Freeman, R., Horowitz, C. R., Richardson, L. D., Nadkarni, G. N., et al. (2025) · International Journal for Equity in Health · doi:10.1186/s12939-025-02419-0 · Cited by 110
Navigating LLM ethics: advancements, challenges, and future directions
Jiao, J., Afroogh, S., Xu, Y., & Phillips, C. (2025) · AI and Ethics · doi:10.1007/s43681-025-00814-5 · Cited by 216
Enhancing Sentiment Analysis in Stock Market Tweets Through BERT-Based Knowledge Transfer
Cicekyurt, E., & Bakal, G. (2025) · Computational Economics · doi:10.1007/s10614-025-10901-8 · Cited by 39
Omar, M., Soffer, S., Agbareia, R., Bragazzi, N. L., Apakama, D. U., Horowitz, C. R., Charney, A. W., Freeman, R., Kummer, B. R., Glicksberg, B. S., et al. (2024) · medRxiv · doi:10.1101/2024.10.29.24316368 · Cited by 19
Extraction of Subjective Information from Large Language Models
Kobayashi, A., & Yamaguchi, S. (2024) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac61105.2024.00253 · Cited by 8
Exploring the Intersection of AI, Language, and Law: A Bibliometric Analysis
Lan, Z., & Zhang, X. (2026) · SAGE Open · doi:10.1177/21582440261431000 · Cited by 9
Zhang, X., He, C., Zhang, P., Gu, H., Gu, N., Shen, Q., Hu, Z., & Lu, T. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714277 · Cited by 11
Salmoria, C. H., & Ramos, W. A. (2024) · Sistema e-Revista CNJ · doi:10.54829/revistacnj.v8i2.618 · Cited by 2
AI Literacy for Legal AI Systems: a Practical Approach
Gültekin-Várkonyi, G. (2025) · Iustum Aequum Salutare · doi:10.69695/ias.2025.4.01 · Cited by 6
Govea, J., Ortiz-Garcés, I., Palacios, P., Navarro, A. M., del Pino, S. M. A., & Villegas-Ch, W. E. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1782405 · Cited by 1
Gendered representations of occupations in large language model generated images and texts
Wen, X., & Zhou, X. (2026) · Social Semiotics · doi:10.1080/10350330.2026.2704561 · Cited by 1
Tian, Y. (2025) · Journal of Computational Methods in Sciences and Engineering · doi:10.1177/14727978251393473 · Cited by 1
Doumanas, D., Soularidis, A., Zafeiropoulos, N., Chatzistamatis, S., Tsekouras, G. E., Saer, A. E., Nathanailidis, C., & Kotis, K. (2026) · Information · doi:10.3390/info17040342
Prioritizing Requirements Using Values and LLMs
Schmid, E., Herrmann, M., Mircea, M., & Schneider, K. A. (2026) · IEEE International Requirements Engineering Conference Workshops (REW) · doi:10.1109/rew72749.2026.00071
Metadata
- Authors
- Bozdag, M., Sevim, N., & Koç, A.
- Affiliations
- Bilkent University (TR)
- Venue
- ACM Transactions on Knowledge Discovery from Data
- Published
- 2024-02-13
- Volume
- 18
- Issue
- 4
- Pages
- 1-26
- ISSN
- 1556-4681 (ISSN-L)
- 1556-472X
- OpenAlex
- W4387735167
- Cited by
- 15
- References
- 89
- Citations by year
- 2026: 5 · 2025: 7 · 2024: 3
- FWCI
- 3.76
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM Transactions on Knowledge Discovery from Data (publishedVersion)
- Bilkent University Institutional Repository (Bilkent University) (submittedVersion, cc-by)
- Funders
- TUBITAK 1001 grant (120E346)
- BAGEP 2023 Young Scientist Award
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Law › Artificial Intelligence in Law
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- gender bias, social bias, contextual language models, BERT, legal NLP, computational law, bias measurement, bias mitigation, fine-tuning, transformer models
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.