GenFair: Systematic Test Generation for Fairness Fault Detection in Large Language Models

TL;DR

GenFair is a novel systematic testing framework that enhances fairness fault detection in large language models by generating diverse, realistic, and intersectional test cases using metamorphic testing techniques.

Contribution

It introduces a metamorphic fairness testing approach that improves detection of complex biases in LLMs over existing template-based methods.

Findings

GenFair achieves higher fault detection rates (0.73/0.69) than baselines.

It produces more diverse and coherent test cases.

GenFair effectively uncovers nuanced fairness violations.

Abstract

Large Language Models (LLMs) are increasingly deployed in critical domains, yet they often exhibit biases inherited from training data, leading to fairness concerns. This work focuses on the problem of effectively detecting fairness violations, especially intersectional biases that are often missed by existing template-based and grammar-based testing methods. Previous approaches, such as CheckList and ASTRAEA, provide structured or grammar-driven test generation but struggle with low test diversity and limited sensitivity to complex demographic interactions. To address these limitations, we propose GenFair, a metamorphic fairness testing framework that systematically generates source test cases using equivalence partitioning, mutation operators, and boundary value analysis. GenFair improves fairness testing by generating linguistically diverse, realistic, and intersectional test cases. It applies metamorphic relations (MR) to derive follow-up cases and detects fairness violations via tone-based comparisons between source and follow-up responses. In experiments with GPT-4.0 and LLaMA-3.0, GenFair outperformed two baseline methods. It achieved a fault detection rate (FDR) of 0.73 (GPT-4.0) and 0.69 (LLaMA-3.0), compared to 0.54/0.51 for template-based and 0.39/0.36 for ASTRAEA. GenFair also showed the highest test case diversity (syntactic:10.06, semantic: 76.68) and strong coherence (syntactic: 291.32, semantic: 0.7043), outperforming both baselines. These results demonstrate the effectiveness of GenFair in uncovering nuanced fairness violations. The proposed method offers a scalable and automated solution for fairness testing and contributes to building more equitable LLMs.