KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910278642302976 |
|---|---|
| author | Davoodi, Farbod Shiyadeh, Seyed Reza Tavakoli Safaei, Pooria Harighi, Sana Gholami, Parsa Amini, Amirali Vanaei, Kimia Firoozi, Emad Azad, Parham Abed Khalaj, Babak Ahmadi, Siavash Payberah, Amir Hossein Rohban, Mohammad Hossein Kolouri, Soheil Diba, Ali |
| author_facet | Davoodi, Farbod Shiyadeh, Seyed Reza Tavakoli Safaei, Pooria Harighi, Sana Gholami, Parsa Amini, Amirali Vanaei, Kimia Firoozi, Emad Azad, Parham Abed Khalaj, Babak Ahmadi, Siavash Payberah, Amir Hossein Rohban, Mohammad Hossein Kolouri, Soheil Diba, Ali |
| contents | Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cultural stereotypes they inherit from training data (rendering women, people of colour, older adults, and non-Western cultures as under-represented or caricatured) become a population-level harm at deployment scale. Existing mitigations either require costly retraining, infeasible for the closed-source backbones that dominate consumer products, or rely on fixed demographic templates that ignore cultural context. We present KG-FairDiff, a model-agnostic, inference-time framework that formalises fairness-aware prompt refinement as a constrained optimisation problem and operationalises it as a closed-loop pipeline: a knowledge graph of ~1,200 culture- and bias-related triples retrieves structured context, an LLM rewriter proposes refinements, and a validator accepts only prompts that reduce a divergence-based fairness loss while preserving semantic fidelity to the user's original intent. We prove a finite-termination bound for the refinement loop, contribute a mathematically consistent evaluation suite linking Bias-P/Bias-W to divergence from target distributions and ENS to KL divergence, and audit eight widely-deployed backbone generators. KG-FairDiff substantially reduces gender, race, age, and intersectional disparities while preserving prompt semantics, offering a practical, deployment-ready route to more equitable generative AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01282 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation Davoodi, Farbod Shiyadeh, Seyed Reza Tavakoli Safaei, Pooria Harighi, Sana Gholami, Parsa Amini, Amirali Vanaei, Kimia Firoozi, Emad Azad, Parham Abed Khalaj, Babak Ahmadi, Siavash Payberah, Amir Hossein Rohban, Mohammad Hossein Kolouri, Soheil Diba, Ali Computer Vision and Pattern Recognition Computers and Society Machine Learning Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cultural stereotypes they inherit from training data (rendering women, people of colour, older adults, and non-Western cultures as under-represented or caricatured) become a population-level harm at deployment scale. Existing mitigations either require costly retraining, infeasible for the closed-source backbones that dominate consumer products, or rely on fixed demographic templates that ignore cultural context. We present KG-FairDiff, a model-agnostic, inference-time framework that formalises fairness-aware prompt refinement as a constrained optimisation problem and operationalises it as a closed-loop pipeline: a knowledge graph of ~1,200 culture- and bias-related triples retrieves structured context, an LLM rewriter proposes refinements, and a validator accepts only prompts that reduce a divergence-based fairness loss while preserving semantic fidelity to the user's original intent. We prove a finite-termination bound for the refinement loop, contribute a mathematically consistent evaluation suite linking Bias-P/Bias-W to divergence from target distributions and ENS to KL divergence, and audit eight widely-deployed backbone generators. KG-FairDiff substantially reduces gender, race, age, and intersectional disparities while preserving prompt semantics, offering a practical, deployment-ready route to more equitable generative AI. |
| title | KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2606.01282 |