Metraipolis › archive › dc_b85f2eacaeea
Fast, Cheap, and Fair? Evaluating Decision Models — arXiv:2611.04510
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04510
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:34:41.811Z
- SHA-256 of the archived text
7c5ebd50323e684805aa9b8f21718179943f5fac08dd6d5e207d4fd3ef610097- Stable URL of this page
https://metraipolis.com/documento/dc_b85f2eacaeea
How to cite
Fast, Cheap, and Fair? Evaluating Decision Models — arXiv:2611.04510 — arXiv (en), https://arxiv.org/abs/2611.04510 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b85f2eacaeea (Metraipolis archive dc_b85f2eacaeea, sha256 7c5ebd50323e684805aa9b8f21718179943f5fac08dd6d5e207d4fd3ef610097)
BibTeX
@misc{dcb85f2eacaeea,
title = {Fast, Cheap, and Fair? Evaluating Decision Models — arXiv:2611.04510},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04510},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b85f2eacaeea; sha256 7c5ebd50323e684805aa9b8f21718179943f5fac08dd6d5e207d4fd3ef610097},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04510. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Industries are increasingly adopting AI-driven systems to automate a wide range of tasks, including high-stakes decisions in human resources, such as candidate screening and recruitment. This makes evaluating their fairness essential, particularly when decisions directly affect individuals' opportunities. Accordingly, the EU AI Act classifies recruitment AI systems as high-risk, imposing strict requirements on their deployment. In this context, compact ``System~1'' decision models offer a fast and cost-efficient alternative to general-purpose LLMs, yet their fairness remains largely unexplored. This article presents the first systematic bias and fairness audit of \jev{}, a typed-decision model targeting recruitment applications. The study evaluates how explicit demographic attributes and implicit candidate cues influence screening scores, rankings, and shortlisting outcomes. These effects are compared against a noise floor derived from name substitutions and typographical variations. The evaluation also examines output validity, latency, and cost. Counterfactual CV datasets and evaluation code are released for reproducibility.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04510 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T18:32:37.326Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).