A database to support the evaluation of gender biases in GPT-4o output
This work addresses ethical risks for users and societies by improving fairness evaluation in LLMs, though it appears incremental in methodology.
The authors tackled the problem of evaluating gender biases in GPT-4o outputs by proposing a novel database construction approach, enabling assessment beyond neutralization without providing concrete numerical results.
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.