LLMs systematically favor resumes they generated themselves over human-written ones, study finds

Researchers conducted a large-scale controlled resume correspondence experiment across 24 occupations and found that LLMs consistently prefer resumes generated by themselves over those written by humans or produced by alternative models, even when content quality is controlled.

Self-preference bias ranges from 67% to 82% across major commercial and open-source models, with candidates using the same LLM as the evaluator 23% to 60% more likely to be shortlisted than equally qualified applicants submitting human-written resumes. The largest disadvantages appear in business-related fields such as sales and accounting.

Simple interventions targeting LLMs' self-recognition capabilities can reduce this bias by more than 50%, suggesting the phenomenon can be mitigated without major system overhauls.