Examining the Cultural Encoding of Gender Bias in LLMs for Low-Resourced African Languages

Large Language Models (LLMs) are deployed in various aspects of everyday life.While the technology could have several benefits, like many socio-technical systems, it also encodes several biases.Trained on large, crawled datasets from the web, these models perpetuate stereotypes and regurgitate representational bias that is rampant in their training data.Languages encode gender in varying ways; some languages are grammatically gendered, while others are not.Bias in the languages themselves may also vary based on cultural, social, and religious contexts.In this paper, we investigate gender bias in LLMs by selecting two languages, Twi and Amharic.Twi is a nongendered African language spoken in Ghana, while Amharic is a gendered language spoken in Ethiopia.Using these two languages on the two ends of the continent and their opposing grammatical gender system, we evaluate LLMs in three tasks: Machine Translation, Image Generation, and Sentence Completion.Our results give insights into the gender bias encoded in LLMs using two low-resourced languages and broaden the conversation on how culture and social structures play a role in disparate system performances.