2 papers
cs.LO2026
Counting Worlds Branching Time Semantics for post-hoc Bias Mitigation in generative AI
Alessandro G. Buda, Giuseppe Primiero, Leonardo Ceragioli +1
Generative AI systems are known to amplify biases present in their training data. While several inference-time mitigation strategies have been proposed, they remain largely empiric…
cs.AI2024
Evaluating AI fairness in credit scoring with the BRIO tool
Greta Coraglia, Francesco A. Genco, Pellegrino Piantadosi +4
We present a method for quantitative, in-depth analyses of fairness issues in AI systems with an application to credit scoring. To this aim we use BRIO, a tool for the evaluation o…