# Gender and Racial Stereotype Detection in Legal Opinion Word Embeddings

arXiv: https://arxiv.org/abs/2203.13369 · HTML: https://mlsanity.com/paper/2203.13369/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 6 of 6)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model](https://mlsanity.com/paper/2008.06460/) (2020)
- [Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination](https://mlsanity.com/paper/1906.00285/) (2019)

## Built on by (most cited first, 4 of 4)

- [Questioning Biases in Case Judgment Summaries: Legal Datasets or Large Language Models?](https://mlsanity.com/paper/2312.00554/) (2023)
- [Statistical Uncertainty in Word Embeddings: GloVe-V](https://mlsanity.com/paper/2406.12165/) (2024)
- [Post-hoc Study of Climate Microtargeting on Social Media Ads with LLMs: Thematic Insights and Fairness Evaluation](https://mlsanity.com/paper/2410.05401/) (2024)
- [For the Underrepresented in Gender Bias Research: Chinese Name Gender Prediction with Heterogeneous Graph Attention Network](https://mlsanity.com/paper/2302.00419/) (2023)

## Abstract (arXiv)

Studies have shown that some Natural Language Processing (NLP) systems encode and replicate harmful biases with potential adverse ethical effects in our society. In this article, we propose an approach for identifying gender and racial stereotypes in word embeddings trained on judicial opinions from U.S. case law. Embeddings containing stereotype information may cause harm when used by downstream systems for classification, information extraction, question answering, or other machine learning systems used to build legal research tools. We first explain how previously proposed methods for identifying these biases are not well suited for use with word embeddings trained on legal opinion text. We then propose a domain adapted method for identifying gender and racial biases in the legal domain. Our analyses using these methods suggest that racial and gender biases are encoded into word embeddings trained on legal opinions. These biases are not mitigated by exclusion of historical data, and appear across multiple large topical areas of the law. Implications for downstream systems that use legal opinion word embeddings and suggestions for potential mitigation strategies based on our observations are also discussed.