Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: van der Linden, Ilona, Kumar, Sahana, Dixit, Arnav, Sudan, Aadi, Danda, Smruthi, Anastasiu, David C., Lukoff, Kai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918411368398848
author van der Linden, Ilona
Kumar, Sahana
Dixit, Arnav
Sudan, Aadi
Danda, Smruthi
Anastasiu, David C.
Lukoff, Kai
author_facet van der Linden, Ilona
Kumar, Sahana
Dixit, Arnav
Sudan, Aadi
Danda, Smruthi
Anastasiu, David C.
Lukoff, Kai
contents As generative AI tools are increasingly used to portray people in professional roles, understanding their racial and gender representational biases is critical. We audit over 1.5 million occupational personas generated by four major large language models - GPT-4, Gemini 2.5, DeepSeek V3.1, and Mistral-medium - across 41 U.S. occupations. Comparing these personas against U.S. Bureau of Labor Statistics (BLS) data, we find that models generate demographics with less variation than real-world data, functionally compressing each occupation toward a dominant demographic profile rather than representing population-level variation. A shift/exaggeration decomposition reveals the structure of these distortions: White (-31pp) and Black (-9pp) workers are consistently underrepresented, while Hispanic (+17pp) and Asian (+12pp) workers are overrepresented, with stereotype exaggeration amplifying existing occupational segregation. These distortions are often extreme, including near-total portrayals of housekeepers as Hispanic and the near-erasure of Black workers from many occupations. Because these patterns recur across models with different institutional and cultural origins, they suggest shared structural sources of bias rather than model-specific artifacts. We argue that auditing generative AI requires evaluation frameworks that examine how synthetic populations systematically reshape demographic visibility across social roles.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21011
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations
van der Linden, Ilona
Kumar, Sahana
Dixit, Arnav
Sudan, Aadi
Danda, Smruthi
Anastasiu, David C.
Lukoff, Kai
Human-Computer Interaction
Artificial Intelligence
Computers and Society
As generative AI tools are increasingly used to portray people in professional roles, understanding their racial and gender representational biases is critical. We audit over 1.5 million occupational personas generated by four major large language models - GPT-4, Gemini 2.5, DeepSeek V3.1, and Mistral-medium - across 41 U.S. occupations. Comparing these personas against U.S. Bureau of Labor Statistics (BLS) data, we find that models generate demographics with less variation than real-world data, functionally compressing each occupation toward a dominant demographic profile rather than representing population-level variation. A shift/exaggeration decomposition reveals the structure of these distortions: White (-31pp) and Black (-9pp) workers are consistently underrepresented, while Hispanic (+17pp) and Asian (+12pp) workers are overrepresented, with stereotype exaggeration amplifying existing occupational segregation. These distortions are often extreme, including near-total portrayals of housekeepers as Hispanic and the near-erasure of Black workers from many occupations. Because these patterns recur across models with different institutional and cultural origins, they suggest shared structural sources of bias rather than model-specific artifacts. We argue that auditing generative AI requires evaluation frameworks that examine how synthetic populations systematically reshape demographic visibility across social roles.
title Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations
topic Human-Computer Interaction
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2510.21011