Probing Gender Bias in Multilingual LLMs: A Case Study of Stereotypes in Persian

2025-09-24 · Ghazal Kalhor, Behnam Bahrak arxiv

Multilingual Large Language Models (LLMs) are increasingly used worldwide, making it essential to ensure they are free from gender bias to prevent representational harm. While prior studies have examined such biases in high-resource languages, low-resource languages remain understudied. In this paper, we propose a template-based probing methodology, validated against real-world data, to uncover gender stereotypes in LLMs. As part of this framework, we introduce the Domain-Specific Gender Skew Index (DS-GSI), a metric that quantifies deviations from gender parity. We evaluate four prominent models, GPT-4o mini, DeepSeek R1, Gemini 2.0 Flash, and Qwen QwQ 32B, across four semantic domains, focusing on Persian, a low-resource language with distinct linguistic features. Our results show that all models exhibit gender stereotypes, with greater disparities in Persian than in English across all domains. Among these, sports reflect the most rigid gender biases. This study underscores the need for inclusive NLP practices and provides a framework for assessing bias in other low-resource languages.

📄 PDF Abstract BibTeX arXiv:2509.20168

Code (0)

등록된 구현이 없습니다.

Disclosure and Mitigation of Gender Bias in LLMs

2024-02-17 · Xiangjue Dong, Yibo Wang, Philip S. Yu, James Caverlee

Large Language Models (LLMs) can generate biased responses. Yet previous direct probing techniques contain either gender mentions or predefined gender stereotypes, which are challenging to comprehensively collect. Hence,…

A Multilingual Perspective on Probing Gender Bias

2024-03-15 · Karolina Stańczak

Gender bias represents a form of systematic negative treatment that targets individuals based on their gender. This discrimination can range from subtle sexist remarks and gendered stereotypes to outright hate speech. Pr…

A Multifaceted Analysis of Social Biases in Large Language Models

2025-12-16 · Xulang Zhang, Rui Mao, Erik Cambria arxiv

Large language models (LLMs) have rapidly become indispensable tools for acquiring information and supporting human decision-making. However, ensuring that these models uphold fairness across varied contexts is critical …

An Information-Theoretic Approach and Dataset for Probing Gender Stereotypes in Multilingual Masked Language Models

2022-07-01 · Findings (NAACL) 2022 7 · Victor Steinborn, Philipp Dufter, Haris Jabbar, Hinrich Schuetze

Bias research in NLP is a rapidly growing and developing field. Similar to CrowS-Pairs (Nangia et al., 2020), we assess gender bias in masked-language models (MLMs) by studying pairs of sentences with gender swapped pers…

Sentence

Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation

2023-11-01 · Xiangjue Dong, Yibo Wang, Philip S. Yu, James Caverlee

Large Language Models (LLMs) can generate biased and toxic responses. Yet most prior work on LLM gender bias evaluation requires predefined gender-related phrases or gender stereotypes, which are challenging to be compre…

Conditional Text Generation Fairness Text Generation