Gender Bias in LLM-generated Interview Responses
This addresses bias in LLM-generated job-related texts, which is an incremental audit for fairness in AI applications.
The study evaluated gender bias in interview responses generated by three LLMs (GPT-3.5, GPT-4, Claude), finding that bias is consistent and aligned with gender stereotypes and job dominance.
LLMs have emerged as a promising tool for assisting individuals in diverse text-generation tasks, including job-related texts. However, LLM-generated answers have been increasingly found to exhibit gender bias. This study evaluates three LLMs (GPT-3.5, GPT-4, Claude) to conduct a multifaceted audit of LLM-generated interview responses across models, question types, and jobs, and their alignment with two gender stereotypes. Our findings reveal that gender bias is consistent, and closely aligned with gender stereotypes and the dominance of jobs. Overall, this study contributes to the systematic examination of gender bias in LLM-generated interview responses, highlighting the need for a mindful approach to mitigate such biases in related applications.