Multi-Group Proportional Representation in Retrieval
–Neural Information Processing Systems
Current approaches to mitigate these representational harms balance the number of retrieved items across population groups defined by a small number of (often binary) attributes. However, most existing methods overlook intersectional groups determined by combinations of group attributes, such as gender, race, and ethnicity.
Neural Information Processing Systems
Oct-10-2025, 17:09:44 GMT
- Country:
- Africa > South Africa (0.04)
- Asia (0.04)
- Europe
- Sweden (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- North America > United States
- Georgia > Fulton County
- Atlanta (0.04)
- Illinois > Cook County
- Chicago (0.04)
- Minnesota (0.04)
- Georgia > Fulton County
- Oceania > New Zealand (0.04)
- South America > Uruguay (0.04)
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (1.00)
- Research Report
- Industry:
- Government (1.00)
- Law (0.67)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Neural Networks > Deep Learning (0.45)
- Statistical Learning > Regression (0.47)
- Natural Language (1.00)
- Representation & Reasoning > Optimization (1.00)
- Vision (1.00)
- Machine Learning
- Information Technology > Artificial Intelligence