mlsanityData to 7 Oct 2026

Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints

arXiv 1707.09457 ↗First posted 29 Jul 2017cs.AI cs.CL cs.CVcited by 420

Not on the map. Why?

Cited by 25 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between co-occurring labels and visual input but risk inadvertently encoding social biases found in web corpora. In this work, we study data and models associated with multilabel object classification and visual semantic role labeling. We find that (a) datasets for these tasks contain significant gender bias and (b) models trained on these datasets further amplify existing bias. For example, the activity cooking is over 33% more likely to involve females than males in a training set, and a trained model further amplifies the disparity to 68% at test time. We propose to inject corpus-level constraints for calibrating existing structured prediction models and design an algorithm based on Lagrangian relaxation for collective inference. Our method results in almost no performance loss for the underlying recognition task but decreases the magnitude of bias amplification by 47.5% and 40.5% for multilabel classification and visual semantic role labeling, respectively.

Key facts. Cited by 420 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 71; 2022: 83; 2023: 111; 2024: 83; 2025: 41; 2026: 31.

420 papers.

Sort:

By area:

  1. 2023Segment Anythingcited by 8,158
  2. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  3. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  4. 2021Ethical and social risks of harm from Language Modelscited by 957
  5. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  6. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  7. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  8. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  9. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 336
  10. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294
  11. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  12. 2023PaLI-X: On Scaling up a Multilingual Vision and Language Modelcited by 254
38 more
  1. 2022DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Modelscited by 230
  2. 2023"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letterscited by 196
  3. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  4. 2022MERLOT Reserve: Neural Script Knowledge through Vision and Language and Soundcited by 184
  5. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 183
  6. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  7. 2021RedCaps: web-curated image-text data created by the people, for the peoplecited by 175
  8. 2021Alignment of Language Agentscited by 167
  9. 2023Debiasing Vision-Language Models via Biased Promptscited by 147
  10. 2021Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologiescited by 128
  11. 2021Gender Bias in Machine Translationcited by 116
  12. 2021Understanding and Evaluating Racial Biases in Image Captioningcited by 108
  13. 2022A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learningcited by 104
  14. 2021Re-imagining Algorithmic Fairness in India and Beyondcited by 102
  15. 2022Benchmarking Spatial Relationships in Text-to-Image Generationcited by 96
  16. 2021Trustworthy AI: A Computational Perspectivecited by 93
  17. 2023Art and the science of generative AI: A deeper divecited by 93
  18. 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
  19. 2021Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Searchcited by 90
  20. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90
  21. 2021A Survey on Gender Bias in Natural Language Processingcited by 89
  22. 2021Mitigating Language-Dependent Ethnic Bias in BERTcited by 87
  23. 2021Pre-trained Language Models in Biomedical Domain: A Systematic Surveycited by 87
  24. 2021Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Developmentcited by 85
  25. 2021A Survey on Bias in Visual Datasetscited by 84
  26. 2021A Study of Face Obfuscation in ImageNetcited by 83
  27. 2024A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trendscited by 82
  28. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  29. 2021Anticipating Safety Issues in E2E Conversational AI: Framework and Toolingcited by 77
  30. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  31. 2021A Survey of Race, Racism, and Anti-Racism in NLPcited by 74
  32. 2023Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learningcited by 69
  33. 2023The Bias Amplification Paradox in Text-to-Image Generationcited by 69
  34. 2022A Systematic Study of Bias Amplificationcited by 65
  35. 2023On the Foundations of Shortcut Learningcited by 64
  36. 2022Theories of "Gender" in NLP Bias Researchcited by 62
  37. 2024OpenBias: Open-set Bias Detection in Text-to-Image Generative Modelscited by 61
  38. 2022FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosiscited by 59

50 most cited of 420 All 420 (JSON)