SOURCE-LINKED INTELLIGENCE

Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Open-weight large language models are rapidly entering hiring pipelines, yet their discriminatory failure modes -- and the regulatory exposure these create under the EU AI Act high-risk classification (Annex III) and U.S. EEOC adverse-impact analysis -- remain poorly understood. We present the first systematic, multi-model audit of open-weight LLMs that treats job-posting language as the primary experimental variable, evaluating six models (Llama 3.2, Mistral, Gemma 3, Qwen 3, Phi 3, DeepSeek-R1) across four controlled experiments that jointly probe recruiter-simulation and job-seeker-simulati

Read original source ↗ Open in workspace

recordType

paper

region

Global