mlsanityData to 7 Oct 2026

IndicFairFace: Balanced Indian Face Dataset for Auditing and Mitigating Geographical Bias in Vision-Language Models

arXiv 2602.12659 ↗First posted 13 Feb 2026cs.CV cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → Social bias and fairness in VLMs

Abstract (arXiv)

Vision-Language Models (VLMs) are known to inherit and amplify societal biases from their web-scale training data with Indian being particularly misrepresented. Existing fairness-aware datasets have significantly improved demographic balance across global race and gender groups, yet they continue to treat Indian as a single monolithic category. The oversimplification ignores the vast intra-national diversity across 28 states and 8 Union Territories of India and leads to representational and geographical bias. To address the limitation, we present IndicFairFace, a novel and balanced face dataset comprising 14,400 images representing geographical diversity of India. Images were sourced ethically from Wikimedia Commons and open-license web repositories and uniformly balanced across states and gender. Using IndicFairFace, we quantify intra-national geographical bias in prominent CLIP-based VLMs and reduce it using post-hoc Iterative Nullspace Projection debiasing approach. We also show that the adopted debiasing approach does not adversely impact the existing embedding space as the average drop in retrieval accuracy on benchmark datasets is less than 1.5 percent. Our work establishes IndicFairFace as the first benchmark to study geographical bias in VLMs for the Indian context.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Social bias and fairness in VLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 34 of its 52 references that are in the map. First posted on arXiv 13 Feb 2026.

Builds on

34 of 52 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Identifying Implicit Social Biases in Vision-Language Models1 Nov
  2. 2023MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Models16 Mar

Other references · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  5. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,163
  6. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  7. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  8. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  9. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 426
  10. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294
  11. 2023Demystifying CLIP Datacited by 265
  12. 2019Gender Bias in Contextualized Word Embeddingscited by 203
20 more
  1. 2017No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing Worldcited by 152
  2. 2019On Measuring and Mitigating Biased Inferences of Word Embeddingscited by 112
  3. 2024Benchmarking Vision Language Models for Cultural Understandingcited by 100
  4. 2023MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Trainingcited by 96
  5. 2019Diversity in Facescited by 77
  6. 2024All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languagescited by 55
  7. 2023Inspecting the Geographical Representativeness of Images from Text-to-Image Modelscited by 44
  8. 2024Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrievalcited by 44
  9. 2017Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approachcited by 43
  10. 2024IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Contextcited by 32
  11. 2023Building Socio-culturally Inclusive Stereotype Resources with Community Engagementcited by 25
  12. 2023Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Modelscited by 17
  13. 2025OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learningcited by 15
  14. 2025Chitrarth: Bridging Vision and Language for a Billion Peoplecited by 10
  15. 2025FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypescited by 9
  16. 2025Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinementcited by 7
  17. 2022Gender Bias in Meta-Embeddingscited by 6
  18. 2025Chitranuvad: Adapting Multi-Lingual LLMs for Multimodal Translationcited by 6
  19. 2025CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Modelscited by 2
  20. 2025Surgeons Are Indian Males and Speech Therapists Are White Females: Auditing Biases in Vision-Language Models for Healthcare Professionalscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026GeoDiv: Framework For Measuring Geographical Diversity In Text-To-Image Models
  2. 2024VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
  3. 2025DemoBias: An Empirical Study to Trace Demographic Biases in Vision Foundation Models
  4. 2026Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples
  5. 2026Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos
  6. 2025Data Matters Most: Auditing Social Bias in Contrastive Vision Language Models
  7. 2024A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models
  8. 2024No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models