Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias

TL;DR

This paper investigates social biases, specifically gender and religious biases, in large language models for Bangla, introducing a dataset and probing techniques to measure and analyze these biases.

Contribution

It presents the first bias assessment study for Bangla LLMs, including a curated dataset and evaluation of probing methods for bias detection.

Findings

Identified social biases in Bangla LLM outputs

Developed a benchmark dataset for bias measurement

Evaluated effectiveness of bias probing techniques

Abstract

The rapid growth of Large Language Models (LLMs) has put forward the study of biases as a crucial field. It is important to assess the influence of different types of biases embedded in LLMs to ensure fair use in sensitive fields. Although there have been extensive works on bias assessment in English, such efforts are rare and scarce for a major language like Bangla. In this work, we examine two types of social biases in LLM generated outputs for Bangla language. Our main contributions in this work are: (1) bias studies on two different social biases for Bangla, (2) a curated dataset for bias measurement benchmarking and (3) testing two different probing techniques for bias detection in the context of Bangla. This is the first work of such kind involving bias assessment of LLMs for Bangla to the best of our knowledge. All our code and resources are publicly available for the progress of bias related research in Bangla NLP.