AI RESEARCH
PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Representative Dataset
arXiv CS.AI
•
ArXi:2603.22714v1 Announce Type: cross We present PopResume, a population-representative resume dataset for causal fairness auditing of LLM- and VLM-based resume screening systems. Unlike existing benchmarks that rely on manually injected graphic information and outcome-level disparities, PopResume is grounded in population statistics and preserves natural attribute relationships, enabling path-specific effect (PSE)-based fairness evaluation.