Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Masoudian, Shahed, Escobedo, Gustavo, Strauss, Hannah, Schedl, Markus
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913975913938944
author Masoudian, Shahed
Escobedo, Gustavo
Strauss, Hannah
Schedl, Markus
author_facet Masoudian, Shahed
Escobedo, Gustavo
Strauss, Hannah
Schedl, Markus
contents As Large Language Models (LLMs) are increasingly used across different applications, concerns about their potential to amplify gender biases in various tasks are rising. Prior research has often probed gender bias using explicit gender cues as counterfactual, or studied them in sentence completion and short question answering tasks. These formats might overlook more implicit forms of bias embedded in generative behavior of longer content. In this work, we investigate gender bias in LLMs using gender stereotypes studied in psychology (e.g., aggressiveness or gossiping) in an open-ended task of narrative generation. We introduce a novel dataset called StereoBias-Stories containing short stories either unconditioned or conditioned on (one, two, or six) random attributes from 25 psychological stereotypes and three task-related story endings. We analyze how the gender contribution in the overall story changes in response to these attributes and present three key findings: (1) While models, on average, are highly biased towards male in unconditioned prompts, conditioning on attributes independent from gender stereotypes mitigates this bias. (2) Combining multiple attributes associated with the same gender stereotype intensifies model behavior, with male ones amplifying bias and female ones alleviating it. (3) Model biases align with psychological ground-truth used for categorization, and alignment strength increases with model size. Together, these insights highlight the importance of psychology-grounded evaluation of LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03292
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes
Masoudian, Shahed
Escobedo, Gustavo
Strauss, Hannah
Schedl, Markus
Computation and Language
Artificial Intelligence
As Large Language Models (LLMs) are increasingly used across different applications, concerns about their potential to amplify gender biases in various tasks are rising. Prior research has often probed gender bias using explicit gender cues as counterfactual, or studied them in sentence completion and short question answering tasks. These formats might overlook more implicit forms of bias embedded in generative behavior of longer content. In this work, we investigate gender bias in LLMs using gender stereotypes studied in psychology (e.g., aggressiveness or gossiping) in an open-ended task of narrative generation. We introduce a novel dataset called StereoBias-Stories containing short stories either unconditioned or conditioned on (one, two, or six) random attributes from 25 psychological stereotypes and three task-related story endings. We analyze how the gender contribution in the overall story changes in response to these attributes and present three key findings: (1) While models, on average, are highly biased towards male in unconditioned prompts, conditioning on attributes independent from gender stereotypes mitigates this bias. (2) Combining multiple attributes associated with the same gender stereotype intensifies model behavior, with male ones amplifying bias and female ones alleviating it. (3) Model biases align with psychological ground-truth used for categorization, and alignment strength increases with model size. Together, these insights highlight the importance of psychology-grounded evaluation of LLMs.
title Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2508.03292