An increasing number of studies have examined the social bias of rapidly developed large language models (LLMs). Although most of these studies have focused on bias occurring in a single social attribute, research in social science has shown that social bias often occurs in the form of intersectionality -- the constitutive and contextualized perspective on bias aroused by social attributes. In this study, we construct the Japanese benchmark inter-JBBQ, designed to evaluate the intersectional bias in LLMs on the question-answering setting. Using inter-JBBQ to analyze GPT-4o and Swallow, we find that biased output varies according to its contexts even with the equal combination of social attributes.

Google's AI programs are still generating woke and controversial answers despite the company claiming to have stripped Gemini of its liberal biases. The initial outrage began last month when the tech giant's image generator depicted historically inaccurate figures including Black Founding Fathers and ethnic minority Nazis in 1940s Germany. Google CEO Sundar Pichai described them as'completely unacceptable' and the company removed the software's ability to produce images this week as a form of damage control. In one of its most shocking answers, it could not tell us which was worse - 'dead-naming' a trans person or unleashing a pandemic on the world. Google's AI programs were accused of being ultra woke after depicting historically inaccurate figures including Black Founding Fathers Gemini also claimed that'neither option is acceptable' when asked whether burning fossil fuels or harvesting human blood was preferable.

Recent conversations around gender and AI have centred around the need to understand gender beyond the binary of male and female. For example, facial recognition technology used by Uber in the US has problems with correctly recognising transgender persons (see here and here). Yet Uber is no exception. The U.S. National Science Foundation, for example, has highlighted research that shows that "facial analysis services performed consistently worse on transgender individuals, and were universally unable to classify non-binary genders." According to CNN Business,¹ "The way a computer sees gender isn't always the same way people see it. A growing number of terms for describing one's gender are becoming common in everyday life."