# Quantifying and Reducing Stereotypes in Word Embeddings

arXiv: https://arxiv.org/abs/1606.06121 · HTML: https://mlsanity.com/paper/1606.06121/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2016.

## Built on by (most cited first, 15 of 15)

- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- [Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey](https://mlsanity.com/paper/2211.05617/) (2022)
- [Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective](https://mlsanity.com/paper/2506.05166/) (2025)
- [Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias](https://mlsanity.com/paper/2204.10365/) (2022)
- [Do Large Language Models Understand Morality Across Cultures?](https://mlsanity.com/paper/2507.21319/) (2025)
- [Counterfactual Multi-Token Fairness in Text Classification](https://mlsanity.com/paper/2202.03792/) (2022)
- [Are fairness metric scores enough to assess discrimination biases in machine learning?](https://mlsanity.com/paper/2306.05307/) (2023)
- [LLMs as mirrors of societal moral standards: reflection of cultural divergence and agreement across ethical topics](https://mlsanity.com/paper/2412.00962/) (2024)
- [Identifying Gender Stereotypes and Biases in Automated Translation from English to Italian using Similarity Networks](https://mlsanity.com/paper/2502.11611/) (2025)
- [Dialectograms: Machine Learning Differences between Discursive Communities](https://mlsanity.com/paper/2302.05657/) (2023)
- [Revisiting The Classics: A Study on Identifying and Rectifying Gender Stereotypes in Rhymes and Poems](https://mlsanity.com/paper/2403.11752/) (2024)
- [Fairness Evaluation for Uplift Modeling in the Absence of Ground Truth](https://mlsanity.com/paper/2403.12069/) (2024)
- [Corpus-Based Approaches to Igbo Diacritic Restoration](https://mlsanity.com/paper/2601.18380/) (2026)
- [Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG](https://mlsanity.com/paper/2606.30989/) (2026)
- [Evaluating the Effects of Prompt Perturbation on Bias and Hallucination in Large Language Models](https://mlsanity.com/paper/2609.35804/) (2026)

## Abstract (arXiv)

Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these stereotypes. In this paper, we initiate the study of gender stereotypes in em word embedding, a popular framework to represent text data. As their use becomes increasingly common, applications can inadvertently amplify unwanted stereotypes. We show across multiple datasets that the embeddings contain significant gender stereotypes, especially with regard to professions. We created a novel gender analogy task and combined it with crowdsourcing to systematically quantify the gender bias in a given embedding. We developed an efficient algorithm that reduces gender stereotype using just a handful of training examples while preserving the useful geometric properties of the embedding. We evaluated our algorithm on several metrics. While we focus on male/female stereotypes, our framework may be applicable to other types of embedding biases.