fairness
Fairness in AI pertains to the ethical consideration of ensuring that models make decisions without bias and uphold equitable treatment across different demographic groups, crucial in maintaining societal trust.
- Beyond Last-Click: An Optimal Mechanism for Ad Attribution
- Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
- Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment
- FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRA
- Improved Algorithms for Fair Matroid Submodular Maximization
- Incentivizing Time-Aware Fairness in Data Sharing
- Preserving Task-Relevant Information Under Linear Concept Removal
- Principled Long-Tailed Generative Modeling via Diffusion Models
- RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation
- Stochastically Dominant Peer Prediction
- The Rashomon Set Has It All: Analyzing Trustworthiness of Trees under Multiplicity
- VMDT: Decoding the Trustworthiness of Video Foundation Models