Gender Bias in Generative AI-assisted Recruitment Processes

Martina Ullasci; Marco Rondina; Riccardo Coppola; Antonio Vetrò

cs.AIMar 12, 2026

Gender Bias in Generative AI-assisted Recruitment Processes

Authors: Martina Ullasci, Marco Rondina, Riccardo Coppola, Antonio Vetrò

Organizations: Department of Control and Computer Engineering Politecnico di Torino, Italy Turin, Italy

Abstract

In recent years, generative artificial intelligence (GenAI) systems have assumed increasingly crucial roles in selection processes, personnel recruitment and analysis of candidates' profiles. However, the employment of large language models (LLMs) risks reproducing, and in some cases amplifying, gender stereotypes and bias already present in the labour market. The objective of this paper is to evaluate and measure this phenomenon, analysing how a state-of-the-art generative model (GPT-5) suggests occupations based on gender and work experience background, focusing on under-35-year-old Italian graduates. The model has been prompted to suggest jobs to 24 simulated candidate profiles, which are balanced in terms of gender, age, experience and professional field. Although no significant differences emerged in job titles and industry, gendered linguistic patterns emerged in the adjectives attributed to female and male candidates, indicating a tendency of the model to associate women with emotional and empathetic traits, while men with strategic and analytical ones. The research raises an ethical question regarding the use of these models in sensitive processes, highlighting the need for transparency and fairness in future digital labour markets.

Figures & tables

Analyze	Occupational suggestions proposed by a state-of-the-art GenAI system
For the purpose of	Identifying whether gender bias emerges in AI-assisted job suggestions and candidate descriptions
With respect to	Differences in suggested job titles, industries and descriptive adjectives
From the viewpoint of	Researchers interested in fairness, ethics, and bias in GenAI
In the context of	Simulated job-seeker profiles of Italian graduates under 35 years old.

TABLE I: Goal-Question-Metric template for the study

Fig. 1: Sample input and results of the interaction with the GenAI

Hypothesis	p-value	Decision
$H1_{0}$ : The gender of the job-seeker has no impact on the suggested job	0.27	Accept
$H2_{0}$ : The gender of the job-seeker has no impact on the suggested job category	0.38	Accept
$H3_{0}$ : The gender of the job-seeker has no impact on the suggested candidate adjectives	0.002	Reject

TABLE II: Results of the statistical analysis

Fig. 2: Distribution of suggested Job title classes by Gender

Fig. 3: Distribution of suggested industry classes by Gender

Fig. 4: Distribution of suggested adjective classes by Gender

AI and Labor

AI and labor studies how artificial intelligence changes jobs, wages, skills, hiring, and the organization and quality of work.

See all 94 papers

Quantifying Gender Bias in Large Language Models: When ChatGPT Becomes a Hiring Manager
Mar 10, 2026Nina Gerszberg, Janka Hamori, Andrew LoGender Bias in Language Models Algorithmic Bias
Massachusetts Institute of Technology Cambridge, Massachusetts, USA
Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment
Sep 16, 2026Kosuke Kitahara, Nobuhiro YamaguchiGender Bias in Language Models AI-Assisted Decision Making
Recruit Co., Ltd. 1-9-2 Marunouchi Chiyoda-ku, Tokyo 100-6640 Japan
Fairness Beyond Anonymization? Demographic Leakage in German LLM-Generated Resumes
Aug 28, 2026Charlotte Leininger, Helena Veit, Matthias Aßenmacher +1Algorithmic Fairness Demographic Bias in Language Models
Department of Statistics, LMU Munich, Munich, Germany · Munich Center for Machine Learning (MCML), Munich, Germany

Mar 10, 2026J/K move · Enter open · S save

Quantifying Gender Bias in Large Language Models: When ChatGPT Becomes a Hiring Manager

Nina Gerszberg, Janka Hamori, Andrew Lo

Massachusetts Institute of Technology Cambridge, Massachusetts, USA

Gender Bias in Language Models Algorithmic Bias Language Model Bias Evaluation LLM Prompting

Open paper AskPDF arXiv

The growing prominence of large language models (LLMs) in daily life has heightened concerns that LLMs exhibit many of the same gender-related biases as their creators. In the context of hiring decisions, we quantify the degree to which LLMs perpetuate societal biases and investigate prompt engineering as a bias mitigation technique. Our findings suggest that for a given resumé, an LLM is more likely to hire a female candidate and perceive them as more qualified, but still recommends lower pay relative to male candidates.

Abstract

AI and Labor

Explore similar work

Quantifying Gender Bias in Large Language Models: When ChatGPT Becomes a Hiring Manager

Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment

Fairness Beyond Anonymization? Demographic Leakage in German LLM-Generated Resumes