More Women, Same Stereotypes: Unpacking the Gender Bias Paradox in Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Evan, Zhan, Run-Jun, Lin, Yan-Bai, Chen, Hung-Hsuan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914378934124544
author Chen, Evan
Zhan, Run-Jun
Lin, Yan-Bai
Chen, Hung-Hsuan
author_facet Chen, Evan
Zhan, Run-Jun
Lin, Yan-Bai
Chen, Hung-Hsuan
contents Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases. This study introduces a novel evaluation framework to uncover gender biases in LLMs: using free-form storytelling to surface biases embedded within the models. A systematic analysis of ten prominent LLMs shows a consistent pattern of overrepresenting female characters across occupations, likely due to supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). Paradoxically, despite this overrepresentation, the occupational gender distributions produced by these LLMs align more closely with human stereotypes than with real-world labor data. This highlights the challenge and importance of implementing balanced mitigation measures to promote fairness and prevent the establishment of potentially new biases. We release the prompts and LLM-generated stories at GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15904
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle More Women, Same Stereotypes: Unpacking the Gender Bias Paradox in Large Language Models
Chen, Evan
Zhan, Run-Jun
Lin, Yan-Bai
Chen, Hung-Hsuan
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases. This study introduces a novel evaluation framework to uncover gender biases in LLMs: using free-form storytelling to surface biases embedded within the models. A systematic analysis of ten prominent LLMs shows a consistent pattern of overrepresenting female characters across occupations, likely due to supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). Paradoxically, despite this overrepresentation, the occupational gender distributions produced by these LLMs align more closely with human stereotypes than with real-world labor data. This highlights the challenge and importance of implementing balanced mitigation measures to promote fairness and prevent the establishment of potentially new biases. We release the prompts and LLM-generated stories at GitHub.
title More Women, Same Stereotypes: Unpacking the Gender Bias Paradox in Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.15904