A database to support the evaluation of gender biases in GPT-4o output

2025/02/28 by Mehner, Luise, Fiedler, Lena Alicija Philine, Ammon, Sabine +1
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2502.20898

Abstract

The widespread application of Large Language Models (LLMs) involves ethical risks for users and societies. A prominent ethical risk of LLMs is the generation of unfair language output that reinforces or exacerbates harm for members of disadvantaged social groups through gender biases (Weidinger et al., 2022; Bender et al., 2021; Kotek et al., 2023). Hence, the evaluation of the fairness of LLM outputs with respect to such biases is a topic of rising interest. To advance research in this field, promote discourse on suitable normative bases and evaluation methodologies, and enhance the reproducibility of related studies, we propose a novel approach to database construction. This approach enables the assessment of gender-related biases in LLM-generated language beyond merely evaluating their degree of neutralization.

Related

• Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias
• Unveiling Gender Bias in Terms of Profession Across LLMs: Analyzing and Addressing Sociological Implications
• GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
• GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models
• Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models