Study Finds AI Hiring Tools Favor AI-Generated Resumes Over Human-Written Ones

Summary

This research paper empirically investigates self-preference bias in large language models (LLMs) within the hiring context. Through a large-scale controlled resume correspondence experiment, the authors find that LLMs consistently prefer resumes generated by themselves over human-written ones or those from alternative models, with self-preference bias ranging from 67% to 82% across major commercial and open-source models. Simulations across 24 occupations show candidates using the same LLM as the evaluator are 23% to 60% more likely to be shortlisted than equally qualified applicants with human-written resumes, with the largest disadvantages in business fields like sales and accounting. The study demonstrates that this bias can be reduced by more than 50% through simple interventions targeting LLMs' self-recognition capabilities, highlighting an overlooked risk in AI-assisted decision-making.