How Fair is Software Fairness Testing?
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| 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 |