Gender Representation and Bias in Indian Civil Service Mock Interviews

TL;DR

This study reveals significant gender bias in Indian civil service mock interview questions and in large language model explanations, supported by a large dataset of interview questions for future research.

Contribution

It introduces a large dataset of interview questions and demonstrates gender bias in both questions and AI explanations, highlighting social biases in Indian civil service preparation.

Findings

Gender bias in interview questions for male and female candidates

Gender bias present in large language model explanations

A new dataset of 51,278 interview questions for social science research

Abstract

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.