DECASTE: Unveiling Caste Stereotypes in Large Language Models through Multi-Dimensional Bias Analysis

TL;DR

This paper introduces DECASTE, a framework for detecting caste biases in large language models across multiple societal dimensions, revealing systematic reinforcement of harmful stereotypes.

Contribution

It presents a novel multi-dimensional bias analysis framework specifically targeting caste biases in LLMs, filling a critical gap in bias evaluation methods.

Findings

LLMs exhibit significant caste biases across socio-cultural, economic, educational, and political dimensions.

Bias scores are higher for marginalized castes like Dalits and Shudras compared to dominant castes.

The study highlights the need for more inclusive bias mitigation strategies in LLM deployment.

Abstract

Recent advancements in large language models (LLMs) have revolutionized natural language processing (NLP) and expanded their applications across diverse domains. However, despite their impressive capabilities, LLMs have been shown to reflect and perpetuate harmful societal biases, including those based on ethnicity, gender, and religion. A critical and underexplored issue is the reinforcement of caste-based biases, particularly towards India's marginalized caste groups such as Dalits and Shudras. In this paper, we address this gap by proposing DECASTE, a novel, multi-dimensional framework designed to detect and assess both implicit and explicit caste biases in LLMs. Our approach evaluates caste fairness across four dimensions: socio-cultural, economic, educational, and political, using a range of customized prompting strategies. By benchmarking several state-of-the-art LLMs, we reveal that these models systematically reinforce caste biases, with significant disparities observed in the treatment of oppressed versus dominant caste groups. For example, bias scores are notably elevated when comparing Dalits and Shudras with dominant caste groups, reflecting societal prejudices that persist in model outputs. These results expose the subtle yet pervasive caste biases in LLMs and emphasize the need for more comprehensive and inclusive bias evaluation methodologies that assess the potential risks of deploying such models in real-world contexts.