Exploring Gender Bias Beyond Occupational Titles

Ahmed Sabir, Rajesh Sharma
7/3/2025
cs.CL

No official code found. Best implementation: ahmedssabir/GenderLex (0 stars, last commit 2025-11-09).

Abstract

In this work, we investigate the correlation between gender and contextual biases, focusing on elements such as action verbs, object nouns, and particularly on occupations. We introduce a novel dataset, GenderLexicon, and a framework that can estimate contextual bias and its related gender bias. Our model can interpret the bias with a score and thus improve the explainability of gender bias. Also, our findings confirm the existence of gender biases beyond occupational stereotypes. To validate our approach and demonstrate its effectiveness, we conduct evaluations on five diverse datasets, including a Japanese dataset.

View on arXivView PDF

Code Implementations(1)

ahmedssabir/GenderLexCommunity100%
01PythonMay 31, 202511 months ago

Similar Papers

Measuring Gender Bias in Job Title Matching for Grammatical Gender Languages

88% match2025

Locating and Mitigating Gender Bias in Large Language Models

86% match2024

Evaluating Gender Bias in Large Language Models

85% match1 repo2024

Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts

85% match2026

Gender bias and stereotypes in Large Language Models

85% match2023

Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples

84% match2023

Cite this paper

@article{sabir2025exploring,
  title  = {Exploring Gender Bias Beyond Occupational Titles},
  author = {Ahmed Sabir and Rajesh Sharma},
  year   = {2025},
  eprint = {2507.02679},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.02679v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.02679.svg)](https://codeofpaper.com/paper/2507.02679)

Discussion