What does this research mean for the field?

Large Language Models (LLMs) exhibit a consistent bias favoring female-named candidates over male-named candidates in job selection scenarios, despite equal qualifications. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.CHALLENGES_CONSENSUS.

What question did this study set out to answer?

The research aims to investigate how gender influences hiring decisions made by large language models using CV evaluations.

February 19, 2026Open Access

Gender and positional biases in LLM-based hiring decisions: evidence from comparative CV/résumé evaluations

Key Points

The research aims to investigate how gender influences hiring decisions made by large language models using CV evaluations.
Experiment with 22 leading large language models (LLMs).
LLMs received pairs of CVs differentiated by male and female names.
Pairs were presented twice with swapped names to control for bias.
Assessments included adding explicit gender fields and neutral identifiers.
Evaluation of individual CVs was also conducted.
All models favored female-named candidates across 70 professions despite equal qualifications.
Explicit gender fields increased preference for female applicants.
Gender-neutral identifiers resulted in balanced selection.
Models rated female CVs slightly higher in isolated assessments, though minimally impactful.
Significant positional bias observed with candidates listed first in prompts.

Abstract

This study examines the choices made by Large Language Models (LLMs) when selecting professional candidates for a job based on their résumés or curricula vitae (CVs). In an experiment involving 22 leading LLMs, each model was systematically given a job description along with a pair of profession-matched CVs—one bearing a male first name, the other a female first name—and asked to select the more suitable candidate for the job. Each CV pair was presented twice, with names swapped to ensure that any observed preferences in candidate selection stemmed from gendered names cues. Despite equalized professional qualifications between genders, all LLMs consistently favored female-named candidates across 70 different professions. Adding an explicit gender field (male/female) to the CVs further increased the preference for female applicants. When gendered names were replaced with gender-neutral identifiers ( i.e ., Candidate A/B), several models displayed a slight preference for selecting “Candidate A”. Counterbalancing gender assignment between these gender-neutral identifiers resulted in gender parity in candidate selection. When asked to rate CVs in isolation rather than compare pairs, LLMs assigned slightly higher average scores to female CVs overall, but the effect size was negligible. Including preferred pronouns (he/him or she/her) next to a candidate’s name slightly increased the odds of the candidate being selected. Finally, most models exhibited a substantial positional bias to select the candidate listed first in the prompt. These findings underscore the need for caution when deploying LLMs in high-stakes autonomous decision-making contexts and raise doubts about whether LLMs consistently apply principled reasoning.

Bookmark

View Full Paper