Formal Specification, Assessment, and Enforcement of Fairness for Generative AIs

arXiv:2404.16663v1 Announce Type: new
Abstract: The risk of reinforcing or exacerbating societal biases and inequalities is growing as generative AI increasingly produces content that resembles human output, from text to images and beyond. Here we formally characterize the notion of fairness for generative AI as a basis for monitoring and enforcing fairness. We define two levels of fairness utilizing the concept of infinite words. The first is the fairness demonstrated on the generated sequences, which is only evaluated on the …

abstract arxiv assessment beyond biases cs.ai cs.cy cs.lg cs.lo cs.se fairness generative human images monitoring notion risk text text to images type