How Fair is Software Fairness Testing?

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Barcomb, Ann, Bento, Mariana Pinheiro, Destefanis, Giuseppe, Licorish, Sherlock, Magalhães, Cleyton, Santos, Ronnie de Souza, Wessel, Mairieli
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914390355214336
author Barcomb, Ann
Bento, Mariana Pinheiro
Destefanis, Giuseppe
Licorish, Sherlock
Magalhães, Cleyton
Santos, Ronnie de Souza
Wessel, Mairieli
author_facet Barcomb, Ann
Bento, Mariana Pinheiro
Destefanis, Giuseppe
Licorish, Sherlock
Magalhães, Cleyton
Santos, Ronnie de Souza
Wessel, Mairieli
contents Software fairness testing is a central method for evaluating AI systems, yet the meaning of fairness is often treated as fixed and universally applicable. This vision paper positions fairness testing as culturally situated and examines the problem across three dimensions. First, fairness metrics encode particular cultural values while marginalizing others. Second, test datasets are predominantly designed from Western contexts, excluding knowledge systems grounded in oral traditions, Indigenous languages, and non-digital communities. Third, fairness testing raises ethical concerns, including the reliance on low-paid data labeling in the Global South, and associated with this, the environmental costs of training and deploying large-scale models, which disproportionately affect climate-vulnerable populations. Addressing these issues requires rethinking fairness testing beyond universal metrics and moving toward evaluation frameworks that respect cultural plurality and acknowledge the right to refuse algorithmic mediation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12511
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle How Fair is Software Fairness Testing?
Barcomb, Ann
Bento, Mariana Pinheiro
Destefanis, Giuseppe
Licorish, Sherlock
Magalhães, Cleyton
Santos, Ronnie de Souza
Wessel, Mairieli
Software Engineering
Software fairness testing is a central method for evaluating AI systems, yet the meaning of fairness is often treated as fixed and universally applicable. This vision paper positions fairness testing as culturally situated and examines the problem across three dimensions. First, fairness metrics encode particular cultural values while marginalizing others. Second, test datasets are predominantly designed from Western contexts, excluding knowledge systems grounded in oral traditions, Indigenous languages, and non-digital communities. Third, fairness testing raises ethical concerns, including the reliance on low-paid data labeling in the Global South, and associated with this, the environmental costs of training and deploying large-scale models, which disproportionately affect climate-vulnerable populations. Addressing these issues requires rethinking fairness testing beyond universal metrics and moving toward evaluation frameworks that respect cultural plurality and acknowledge the right to refuse algorithmic mediation.
title How Fair is Software Fairness Testing?
topic Software Engineering
url https://arxiv.org/abs/2603.12511