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

• URL: http://arxiv.org/abs/2011.12086v1
• Date: Tue, 24 Nov 2020 13:45:14 GMT
• Title: Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis
• Authors: Michael A. Lepori
• Abstract summary: 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.
• Score: 3.8580784887142774
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing [72.0343083866144]
  This paper introduces the GenderBias-emphVL benchmark to evaluate occupation-related gender bias in Large Vision-Language Models. Using our benchmark, we extensively evaluate 15 commonly used open-source LVLMs and state-of-the-art commercial APIs. Our findings reveal widespread gender biases in existing LVLMs.
  arXiv  Detail & Related papers  (2024-06-30T05:55:15Z)
• What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations [62.91799637259657]
  Do large language models (LLMs) exhibit sociodemographic biases, even when they decline to respond? We study this research question by probing contextualized embeddings and exploring whether this bias is encoded in its latent representations. We propose a logistic Bradley-Terry probe which predicts word pair preferences of LLMs from the words' hidden vectors.
  arXiv  Detail & Related papers  (2023-11-30T18:53:13Z)
• VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution [80.57383975987676]
  VisoGender is a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
  arXiv  Detail & Related papers  (2023-06-21T17:59:51Z)
• Debiasing Word Embeddings with Nonlinear Geometry [37.88933175338274]
  This work studies biases associated with multiple social categories. Individual biases intersect non-trivially over a one-dimensional subspace. We then construct an intersectional subspace to debias for multiple social categories using the nonlinear geometry of individual biases.
  arXiv  Detail & Related papers  (2022-08-29T21:40:27Z)
• Evidence for Hypodescent in Visual Semantic AI [4.1804353242318255]
  Multiracial people are more likely to be assigned a racial or ethnic label corresponding to a minority or disadvantaged racial or ethnic group than to the equivalent majority or advantaged group. A face morphing experiment grounded in psychological research demonstrates hypodescent. We show that the stereotype-congruent pleasantness association of an image correlates with association with the Black text label in CLIP.
  arXiv  Detail & Related papers  (2022-05-22T06:46:39Z)
• Fairness for Image Generation with Uncertain Sensitive Attributes [97.81354305427871]
  This work tackles the issue of fairness in the context of generative procedures, such as image super-resolution. While traditional group fairness definitions are typically defined with respect to specified protected groups, we emphasize that there are no ground truth identities. We show that the natural extension of demographic parity is strongly dependent on the grouping, and emphimpossible to achieve obliviously.
  arXiv  Detail & Related papers  (2021-06-23T06:17:17Z)
• WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings [39.87681037622605]
  We present WordBias, an interactive visual tool designed to explore biases against intersectional groups encoded in word embeddings. Given a pretrained static word embedding, WordBias computes the association of each word along different groups based on race, age, etc.
  arXiv  Detail & Related papers  (2021-03-05T11:04:35Z)
• One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision [75.82110684355979]
  We study the racial system encoded by computer vision datasets supplying categorical race labels for face images. We find that each dataset encodes a substantially unique racial system, despite nominally equivalent racial categories. We find evidence that racial categories encode stereotypes, and exclude ethnic groups from categories on the basis of nonconformity to stereotypes.
  arXiv  Detail & Related papers  (2021-02-03T22:50:04Z)
• Characterizing Intersectional Group Fairness with Worst-Case Comparisons [0.0]
  We discuss why fairness metrics need to be looked at under the lens of intersectionality. We suggest a simple worst case comparison method to expand the definitions of existing group fairness metrics. We conclude with the social, legal and political framework to handle intersectional fairness in the modern context.
  arXiv  Detail & Related papers  (2021-01-05T17:44:33Z)
• Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases [10.713568409205077]
  State-of-the-art neural language models generate dynamic word embeddings dependent on the context in which the word appears. We introduce the Contextualized Embedding Association Test (CEAT), that can summarize the magnitude of overall bias in neural language models. We develop two methods, Intersectional Bias Detection (IBD) and Emergent Intersectional Bias Detection (EIBD), to automatically identify the intersectional biases and emergent intersectional biases from static word embeddings.
  arXiv  Detail & Related papers  (2020-06-06T19:49:50Z)
• Multi-Dimensional Gender Bias Classification [67.65551687580552]
  Machine learning models can inadvertently learn socially undesirable patterns when training on gender biased text. We propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information.
  arXiv  Detail & Related papers  (2020-05-01T21:23:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.