mlsanityData to 7 Oct 2026

FairRAG: Fair Human Generation via Fair Retrieval Augmentation

arXiv 2403.19964 ↗First posted 29 Mar 2024cs.CV cs.CY cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

Existing text-to-image generative models reflect or even amplify societal biases ingrained in their training data. This is especially concerning for human image generation where models are biased against certain demographic groups. Existing attempts to rectify this issue are hindered by the inherent limitations of the pre-trained models and fail to substantially improve demographic diversity. In this work, we introduce Fair Retrieval Augmented Generation (FairRAG), a novel framework that conditions pre-trained generative models on reference images retrieved from an external image database to improve fairness in human generation. FairRAG enables conditioning through a lightweight linear module that projects reference images into the textual space. To enhance fairness, FairRAG applies simple-yet-effective debiasing strategies, providing images from diverse demographic groups during the generative process. Extensive experiments demonstrate that FairRAG outperforms existing methods in terms of demographic diversity, image-text alignment, and image fidelity while incurring minimal computational overhead during inference.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 29 Mar 2024.

Builds on

29 of 47 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  8. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  9. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  10. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  11. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  12. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
17 more
  1. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  2. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,099
  3. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  4. 2023Unified Concept Editing in Diffusion Modelscited by 377
  5. 2023InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuningcited by 343
  6. 2023FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attentioncited by 313
  7. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  8. 2022DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Modelscited by 230
  9. 2023Stable Bias: Analyzing Societal Representations in Diffusion Modelscited by 225
  10. 2022Re-Imagen: Retrieval-Augmented Text-to-Image Generatorcited by 208
  11. 2023Fair Diffusion: Instructing Text-to-Image Generation Models on Fairnesscited by 149
  12. 2022How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?cited by 92
  13. 2019FairFace: Face Attribute Dataset for Balanced Race, Gender, and Agecited by 87
  14. 2023ITI-GEN: Inclusive Text-to-Image Generationcited by 64
  15. 2023Analyzing Bias in Diffusion-based Face Generation Modelscited by 45
  16. 2021Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialogcited by 33
  17. 2017Human Skin Detection Using RGB, HSV and YCbCr Color Modelscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 20; 2026: 5.

34 papers.

Sort:

By area:

  1. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  2. 2024Current state of LLM Risks and AI Guardrailscited by 44
  3. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 29
  4. 2024Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systemscited by 26
  5. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodescited by 25
  6. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Surveycited by 20
  7. 2024BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Modelscited by 17
  8. 2024Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generationcited by 15
  9. 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunitiescited by 11
  10. 2025Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attentioncited by 9
  11. 2025Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMscited by 8
  12. 2025Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attackscited by 8
22 more
  1. 2026Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guaranteescited by 7
  2. 2024VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversarycited by 6
  3. 2025Mitigating Bias in RAG: Controlling the Embeddercited by 6
  4. 2025RAG-Adapter: A Plug-and-Play RAG-enhanced Framework for Long Video Understandingcited by 6
  5. 2025Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systemscited by 6
  6. 2025AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Datacited by 5
  7. 2025Implicit Bias Injection Attacks against Text-to-Image Diffusion Modelscited by 4
  8. 2025Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifierscited by 4
  9. 2025ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generationcited by 4
  10. 2024RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidancecited by 3
  11. 2025Beyond Overcorrection: Evaluating Diversity in T2I Models with DivBenchcited by 2
  12. 2024Constructing Fair Latent Space for Intersection of Fairness and Explainabilitycited by 1
  13. 2025From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascadescited by 1
  14. 2025Fairness Testing in Retrieval-Augmented Generation: How Small Perturbations Reveal Bias in Small Language Modelscited by 1
  15. 2025How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositionscited by 1
  16. 2026DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generationcited by 1
  17. 2026BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifierscited by 1
  18. 2026Training-Free Debiasing of Diffusion Models via CLIP-Guided Denoising Optimizationcited by 1
  19. 2025The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generationcited by 0
  20. 2025FAIRTOPIA: Envisioning Multi-Agent Guardianship for Disrupting Unfair AI Pipelinescited by 0
  21. 2025Retrieval Augmented Comic Image Generationcited by 0
  22. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Fair Text-to-Image Diffusion via Fair Mapping
  2. 2025FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
  3. 2024FairCoT: Enhancing Fairness in Text-to-Image Generation via Chain of Thought Reasoning with Multimodal Large Language Models
  4. 2023Mitigating Test-Time Bias for Fair Image Retrieval
  5. 2025A Framework for Benchmarking Fairness-Utility Trade-offs in Text-to-Image Models via Pareto Frontiers
  6. 2025FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance
  7. 2026BAFIS: Dataset + Framework to assess occupational Bias and Human Preference in modern Text-to-image Models
  8. 2025Aligned but Stereotypical? How System Prompts Shape Demographic Bias in LLM-Based Text-to-Image Models