# Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings

arXiv: https://arxiv.org/abs/2006.01938 · HTML: https://mlsanity.com/paper/2006.01938/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2020.

## Built on by (most cited first, 20 of 20)

- [Choose Your Lenses: Flaws in Gender Bias Evaluation](https://mlsanity.com/paper/2210.11471/) (2022)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric](https://mlsanity.com/paper/2402.06900/) (2024)
- [Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey](https://mlsanity.com/paper/2211.05617/) (2022)
- [Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation](https://mlsanity.com/paper/2305.14016/) (2023)
- [WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings](https://mlsanity.com/paper/2103.03598/) (2021)
- [Evaluating the Construct Validity of Text Embeddings with Application to Survey Questions](https://mlsanity.com/paper/2202.09166/) (2022)
- [Trustworthy Social Bias Measurement](https://mlsanity.com/paper/2212.11672/) (2022)
- [Social Norm Bias: Residual Harms of Fairness-Aware Algorithms](https://mlsanity.com/paper/2108.11056/) (2021)
- [Marked Attribute Bias in Natural Language Inference](https://mlsanity.com/paper/2109.14039/) (2021)
- [Good-Enough Example Extrapolation](https://mlsanity.com/paper/2109.05602/) (2021)
- [On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias](https://mlsanity.com/paper/2110.05301/) (2021)
- [Second Order WinoBias (SoWinoBias) Test Set for Latent Gender Bias Detection in Coreference Resolution](https://mlsanity.com/paper/2109.14047/) (2021)
- [Disentangling Societal Inequality from Model Biases: Gender Inequality in Divorce Court Proceedings](https://mlsanity.com/paper/2307.10200/) (2023)
- [Algorithmic Fairness: A Tolerance Perspective](https://mlsanity.com/paper/2405.09543/) (2024)
- [Mitigating Gender Bias in Contextual Word Embeddings](https://mlsanity.com/paper/2411.12074/) (2024)
- [Exploring and Mitigating Gender Bias in Encoder-Based Transformer Models](https://mlsanity.com/paper/2511.00519/) (2025)
- [Assessing Linguistic Generalisation in Language Models: A Dataset for Brazilian Portuguese](https://mlsanity.com/paper/2305.14070/) (2023)
- [Detecting and Mitigating Indirect Stereotypes in Word Embeddings](https://mlsanity.com/paper/2305.14574/) (2023)
- [Two Centuries of Sexism in British Parliament: A Computational Analysis of Women's Representation in the Hansard Corpus](https://mlsanity.com/paper/2608.30485/) (2026)

## Abstract (arXiv)

Word embeddings are the standard model for semantic and syntactic representations of words. Unfortunately, these models have been shown to exhibit undesirable word associations resulting from gender, racial, and religious biases. Existing post-processing methods for debiasing word embeddings are unable to mitigate gender bias hidden in the spatial arrangement of word vectors. In this paper, we propose RAN-Debias, a novel gender debiasing methodology which not only eliminates the bias present in a word vector but also alters the spatial distribution of its neighbouring vectors, achieving a bias-free setting while maintaining minimal semantic offset. We also propose a new bias evaluation metric - Gender-based Illicit Proximity Estimate (GIPE), which measures the extent of undue proximity in word vectors resulting from the presence of gender-based predilections. Experiments based on a suite of evaluation metrics show that RAN-Debias significantly outperforms the state-of-the-art in reducing proximity bias (GIPE) by at least 42.02%. It also reduces direct bias, adding minimal semantic disturbance, and achieves the best performance in a downstream application task (coreference resolution).