# Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis

arXiv: https://arxiv.org/abs/2011.12086 · HTML: https://mlsanity.com/paper/2011.12086/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 12 of 12)

- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [A Survey of Race, Racism, and Anti-Racism in NLP](https://mlsanity.com/paper/2106.11410/) (2021)
- [Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens](https://mlsanity.com/paper/2110.00521/) (2021)
- [MIST: Mitigating Intersectional Bias with Disentangled Cross-Attention Editing in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2403.19738/) (2024)
- [Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models](https://mlsanity.com/paper/2310.00313/) (2023)
- [Measuring Intersectional Biases in Historical Documents](https://mlsanity.com/paper/2305.12376/) (2023)
- [Debiasing Word Embeddings with Nonlinear Geometry](https://mlsanity.com/paper/2208.13899/) (2022)
- [Assessing the quality and coherence of word embeddings after SCM-based intersectional bias mitigation](https://mlsanity.com/paper/2601.04393/) (2026)
- [Who is better at math, Jenny or Jingzhen? Uncovering Stereotypes in Large Language Models](https://mlsanity.com/paper/2407.06917/) (2024)
- [Erasing 'Ugly' from the Internet: Propagation of the Beauty Myth in Text-Image Models](https://mlsanity.com/paper/2511.00749/) (2025)
- [A Novel Approach to Fairness in Automated Decision-Making using Affective Normalization](https://mlsanity.com/paper/2205.00819/) (2022)
- [Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups](https://mlsanity.com/paper/2510.06974/) (2025)

## Abstract (arXiv)

We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of intersectional biases against Black women. We show that these embeddings represent Black women as simultaneously less feminine than White women, and less Black than Black men. This finding aligns with intersectionality theory, which argues that multiple identity categories (such as race or sex) layer on top of each other in order to create unique modes of discrimination that are not shared by any individual category.