mlsanityData to 14 Oct 2026

Run Like a Girl! Sports-Related Gender Bias in Language and Vision

arXiv 2305.14468 ↗First posted 23 May 2023cs.CV cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Gender bias in Language and Vision datasets and models has the potential to perpetuate harmful stereotypes and discrimination. We analyze gender bias in two Language and Vision datasets. Consistent with prior work, we find that both datasets underrepresent women, which promotes their invisibilization. Moreover, we hypothesize and find that a bias affects human naming choices for people playing sports: speakers produce names indicating the sport (e.g. 'tennis player' or 'surfer') more often when it is a man or a boy participating in the sport than when it is a woman or a girl, with an average of 46% vs. 35% of sports-related names for each gender. A computational model trained on these naming data reproduces the bias. We argue that both the data and the model result in representational harm against women.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 21 of its 69 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

21 of 69 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  6. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,492
  7. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  8. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,312
  9. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  10. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
  11. 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
  12. 2018Gender Bias in Coreference Resolutioncited by 442
9 more
  1. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  2. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  3. 2015YFCC100M: The New Data in Multimedia Researchcited by 235
  4. 2018Overcoming Language Priors in Visual Question Answering with Adversarial Regularizationcited by 105
  5. 2022Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluationcited by 59
  6. 2021Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Modelscited by 52
  7. 2019Exposing and Correcting the Gender Bias in Image Captioning Datasets and Modelscited by 36
  8. 2022Robust Conversational Agents against Imperceptible Toxicity Triggerscited by 23
  9. 2021Do Language Models Perform Generalizable Commonsense Inference?cited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2023SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examplescited by 53
  2. 2024Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigationcited by 17
  3. 2023Probing Intersectional Biases in Vision-Language Models with Counterfactual Examplescited by 5
  4. 2025Attention IoU: Examining Biases in CelebA using Attention Mapscited by 3
  5. 2026Investigating Associational Biases in Inter-Model Communication of Large Generative Modelscited by 1
  6. 2024Principles of semantic and functional efficiency in grammatical patterningcited by 0