# Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective

Source: [Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective](<https://www.sota2.com/research/paper/68fa7a321e209131cea81ac1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:14:13.950Z

Authors: Hitomi Yanaka, Xinqi He, Jie Lu, Namgi Han, Sunjin Oh, Ryoma Kumon, Yuma Matsuoka, Katsuhiko Watabe, Yuko Itatsu

Published: 2025-06-14T03:30:07.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.12327>)

[PDF](<https://arxiv.org/pdf/2506.12327.pdf>)
