Metraipolis › archive › dc_0f6a4e1ada65
Monocultural Biases: Correlated biases in large language models lead to unequal systemic exclusion rates in hiring — arXiv:2609.22169
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22169
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:49:10.565Z
- SHA-256 of the archived text
6d4bec1cb7c2ba19645f85f50e24c34a6a51fdb7430ed3cd525257d996d1d1a9- Stable URL of this page
https://metraipolis.com/documento/dc_0f6a4e1ada65
How to cite
Monocultural Biases: Correlated biases in large language models lead to unequal systemic exclusion rates in hiring — arXiv:2609.22169 — arXiv (en), https://arxiv.org/abs/2609.22169 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f6a4e1ada65 (Metraipolis archive dc_0f6a4e1ada65, sha256 6d4bec1cb7c2ba19645f85f50e24c34a6a51fdb7430ed3cd525257d996d1d1a9)
BibTeX
@misc{dc0f6a4e1ada65,
title = {Monocultural Biases: Correlated biases in large language models lead to unequal systemic exclusion rates in hiring — arXiv:2609.22169},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22169},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f6a4e1ada65; sha256 6d4bec1cb7c2ba19645f85f50e24c34a6a51fdb7430ed3cd525257d996d1d1a9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22169. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Employers are increasingly using large language models (LLMs) to automate their hiring process. This paper investigates the risk of monocultural biases, in which the widespread deployment of large language models homogenizes biases across the labor market, leading to greater systemic exclusion for certain demographic groups. For ten LLMs, we measure hiring biases across their base and post-trained versions to identify which stage, pre-training or post-training, lead to monocultural biases. We find that, compared to their base models, post-trained models are 3.6% less likely to callback older applicants. This negative shift occurs in eight of the ten models that we evaluate. Post-trained models have much more correlated decisions than base models which is likely driven by human capital traits like skills or college major. However, greater consensus among models increases global systemic exclusion rates from 5.6% to 17.3% and exacerbates demographic inequalities, with intersectional systemic exclusion rates ranging from 12.2% to 21.7% for post-trained models. We find that this inequality is primarily driven by age-based discrimination that is exacerbated in post-training. These results indicate that while post-training techniques may improve models' abilities to select the best applicants, they may raise systemic inequality risks for those at the margin by uniformly introducing new biases. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Computers and Society (cs.CY); General Economics (econ.GN). Pagina del lavoro: https://arxiv.org/abs/2609.22169 — 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 2026-10-09T06:48:44.861Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).