SOURCE-LINKED INTELLIGENCE
Beyond the Name: Demographic Leakage in De-Identified Résumés and Evaluation Artifacts in LLM Bias Audits
De-identified résumé screening assumes that redacting explicit fields prevents ethnocultural inference; however, recent audits attribute residual leakage to declared languages. We investigate whether eliminating language fields resolves this leakage across nine open-weight models and 620 counterfactual résumés. By holding language attributes strictly identical, we isolate unstructured prose across five ethnocultural conditions and three cue-salience tiers. Target-group recovery averages 0.757 overall and saturates at 1.000 under high salience, demonstrating that non-language prose sustains dem
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-15T01:48:44.000Z
First collected: 2026-09-20T09:01:24.920Z. This is not the publication date.