Gender Representation and Bias in Indian Civil Service Mock Interviews

ACL ARR 2025 May Submission5572 Authors

Abstract: Online educational resources often serve as a great leveler for broadening participation. However, unlike traditional educational resources, little or no computational audits for bias exist for such resources. This paper investigates online educational resources for Indian civil service exams, one of the most fiercely competed exams in the world. Our paper makes three key contributions. First, via a substantial corpus of 51,366 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 51,366 interview questions that can inform future social science studies.

Paper Type: Long

Research Area: Computational Social Science and Cultural Analytics

Research Area Keywords: Computational Social Science and Cultural Analytics, Ethics, Bias, and Fairness, NLP Applications

Contribution Types: Data resources, Data analysis

Languages Studied: English

Submission Number: 5572