Which Demographic Features Are Relevant for Individual Fairness Evaluation of U.S. Recidivism Risk Assessment Tools?
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917048671535104 |
|---|---|
| author | Nguyen, Tin Trung Xu, Jiannan Nguyen-Le, Phuong-Anh Lazar, Jonathan Braman, Donald Daumé III, Hal Jelveh, Zubin |
| author_facet | Nguyen, Tin Trung Xu, Jiannan Nguyen-Le, Phuong-Anh Lazar, Jonathan Braman, Donald Daumé III, Hal Jelveh, Zubin |
| contents | Despite its constitutional relevance, the technical ``individual fairness'' criterion has not been operationalized in U.S. state or federal statutes/regulations. We conduct a human subjects experiment to address this gap, evaluating which demographic features are relevant for individual fairness evaluation of recidivism risk assessment (RRA) tools. Our analyses conclude that the individual similarity function should consider age and sex, but it should ignore race. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09868 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Which Demographic Features Are Relevant for Individual Fairness Evaluation of U.S. Recidivism Risk Assessment Tools? Nguyen, Tin Trung Xu, Jiannan Nguyen-Le, Phuong-Anh Lazar, Jonathan Braman, Donald Daumé III, Hal Jelveh, Zubin Computers and Society Artificial Intelligence Human-Computer Interaction Despite its constitutional relevance, the technical ``individual fairness'' criterion has not been operationalized in U.S. state or federal statutes/regulations. We conduct a human subjects experiment to address this gap, evaluating which demographic features are relevant for individual fairness evaluation of recidivism risk assessment (RRA) tools. Our analyses conclude that the individual similarity function should consider age and sex, but it should ignore race. |
| title | Which Demographic Features Are Relevant for Individual Fairness Evaluation of U.S. Recidivism Risk Assessment Tools? |
| topic | Computers and Society Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2505.09868 |