← Search

Carina Prunkl

2 accepted papers

2025

Fairness-Aware Interactive Target Variable Definition

IJCAI 2025

Machine learning requires defining one's target variable for predictions or decisions, a process that can have profound implications on fairness, since biases are often encoded in target variable definition itself, before any data collection or training. The downstream impacts of target variable def

Cited by 0SourcePDFScholar
2023

LUCID: Exposing Algorithmic Bias through Inverse Design

AAAI 2023technical

AI systems can create, propagate, support, and automate bias in decision-making processes. To mitigate biased decisions, we both need to understand the origin of the bias and define what it means for an algorithm to make fair decisions. Most group fairness notions assess a model's equality of outcom…

Cited by 3SourcePDFScholar