Gender Representation and Bias in Indian Civil Service Mock Interviews
This work addresses gender bias in civil service interviews and AI models, providing a dataset for social science studies, but it is incremental as it applies existing methods to new data.
The paper analyzed 51,278 mock interview questions from Indian civil service candidates and found stark gender bias in the questions asked to male and female candidates, with experiments showing strong gender bias in large language models' explanations on gender inference tasks.
This paper makes three key contributions. First, via a substantial corpus of 51,278 interview questions sourced from 888 YouTube videos of mock interviews of Indian civil service candidates, we demonstrate stark gender bias in the broad nature of questions asked to male and female candidates. Second, our experiments with large language models show a strong presence of gender bias in explanations provided by the LLMs on the gender inference task. Finally, we present a novel dataset of 51,278 interview questions that can inform future social science studies.