Global Voices, Local Biases: Socio-Cultural Prejudices across Languages
This work addresses the lack of bias analysis in global languages for researchers and practitioners in AI ethics, though it is incremental as it extends existing methods to more languages and dimensions.
The authors tackled the problem of limited bias studies in non-Western languages by scaling the Word Embedding Association Test to 24 languages and analyzing new bias dimensions like toxicity and ableism, resulting in a comprehensive dataset and findings that highlight socio-cultural prejudices across diverse linguistic contexts.
Human biases are ubiquitous but not uniform: disparities exist across linguistic, cultural, and societal borders. As large amounts of recent literature suggest, language models (LMs) trained on human data can reflect and often amplify the effects of these social biases. However, the vast majority of existing studies on bias are heavily skewed towards Western and European languages. In this work, we scale the Word Embedding Association Test (WEAT) to 24 languages, enabling broader studies and yielding interesting findings about LM bias. We additionally enhance this data with culturally relevant information for each language, capturing local contexts on a global scale. Further, to encompass more widely prevalent societal biases, we examine new bias dimensions across toxicity, ableism, and more. Moreover, we delve deeper into the Indian linguistic landscape, conducting a comprehensive regional bias analysis across six prevalent Indian languages. Finally, we highlight the significance of these social biases and the new dimensions through an extensive comparison of embedding methods, reinforcing the need to address them in pursuit of more equitable language models. All code, data and results are available here: https://github.com/iamshnoo/weathub.