Exploring White Fragility in Large Language Models
Janga Bussaja · International Journal of Computer Science and Information Technology · 2024
This paper evaluates the understanding and biases of large language models (LLMs) regarding racism by comparing their responses to those of prominent African-centered scholars, Dr. Amos Wilson and Dr. Frances Cress Welsing. The study identifies racial biases in LLMs, illustrating the critical need for specialized AI systems like "Smoky," designed to address systemic racism with a foundation in African-centered scholarship. By highlighting disparities and potential biases in LLM responses, the research aims to contribute to the development of more culturally aware and contextually sensitive AI systems.