There is a fast-growing literature in addressing the fairness of AI models (fair-AI), with a continuous stream of new concep- tual frameworks, methods, and tools. How much can we trust them? How much do they actually impact society? We take a critical focus on fair-AI and survey issues, simplifications, and mistakes that researchers and practitioners often under- estimate, which in turn can undermine the trust on fair-AI and limit its contribution to society. In particular, we discuss the hyper-focus on fairness metrics and on optimizing their average performances. We instantiate this observation by dis- cussing the Yule’s effect of fair-AI tools: being fair on average does not imply being fair in contexts that matter. We conclude that the use of fair-AI methods should be complemented with the design, development, and verification practices that are commonly summarized under the umbrella of trustworthy AI
Can We Trust Fair-AI?
Alvarez, Jose M.;Pugnana, Andrea;State, Laura;
2023
Abstract
There is a fast-growing literature in addressing the fairness of AI models (fair-AI), with a continuous stream of new concep- tual frameworks, methods, and tools. How much can we trust them? How much do they actually impact society? We take a critical focus on fair-AI and survey issues, simplifications, and mistakes that researchers and practitioners often under- estimate, which in turn can undermine the trust on fair-AI and limit its contribution to society. In particular, we discuss the hyper-focus on fairness metrics and on optimizing their average performances. We instantiate this observation by dis- cussing the Yule’s effect of fair-AI tools: being fair on average does not imply being fair in contexts that matter. We conclude that the use of fair-AI methods should be complemented with the design, development, and verification practices that are commonly summarized under the umbrella of trustworthy AIFile | Dimensione | Formato | |
---|---|---|---|
CanWeTrustFairAI.pdf
accesso aperto
Tipologia:
Published version
Licenza:
Solo Lettura
Dimensione
234.41 kB
Formato
Adobe PDF
|
234.41 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.