AI Alignment Amplifies Demographic Biases in Hiring Decisions, Study Finds

Jul 16, 2026

A preprint study analyzing 29 language models across 177 occupations finds that these models incorporate demographic information into simulated hiring decisions, advantaging female and Black candidates while penalizing disabled candidates. The research shows that post-training alignment—intended to make models more helpful and aligned with human preferences—substantially amplifies these demographic effects, with the female and Black advantage increasing by nearly 400% and the disability penalty worsening by over 150%.

Why it matters: The findings highlight that alignment processes, while designed to improve AI behavior, can unintentionally exacerbate certain forms of discrimination, particularly against disabled individuals, in high-stakes contexts like hiring.

Full story at: arXiv Computers and Society ↗