Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models
This addresses bias and fairness issues for users in the Global South, particularly India, by highlighting gaps in existing research.
The paper tackles the problem of Western-centric bias in large language models (LLMs) by quantifying stereotypical bias in an Indian context using the Indian-BhED dataset, finding that models like GPT-2 and GPT-3.5 show high propensities for caste (63-79%) and religious (69-72%) stereotypes.
Large Language Models (LLMs), now used daily by millions, can encode societal biases, exposing their users to representational harms. A large body of scholarship on LLM bias exists but it predominantly adopts a Western-centric frame and attends comparatively less to bias levels and potential harms in the Global South. In this paper, we quantify stereotypical bias in popular LLMs according to an Indian-centric frame through Indian-BhED, a first of its kind dataset, containing stereotypical and anti-stereotypical examples in the context of caste and religious stereotypes in India. We find that the majority of LLMs tested have a strong propensity to output stereotypes in the Indian context, especially when compared to axes of bias traditionally studied in the Western context, such as gender and race. Notably, we find that GPT-2, GPT-2 Large, and GPT 3.5 have a particularly high propensity for preferring stereotypical outputs as a percent of all sentences for the axes of caste (63-79%) and religion (69-72%). We finally investigate potential causes for such harmful behaviour in LLMs, and posit intervention techniques to reduce both stereotypical and anti-stereotypical biases. The findings of this work highlight the need for including more diverse voices when researching fairness in AI and evaluating LLMs.