Examining Regional Stereotypes in Doubao v1.6: A Story Completion Study

DOI

10.2991/978-2-38476-551-5_129How to use a DOI?

Keywords

Large Language Models (LLMs); Regional Stereotypes; Cultural Bias; Doubao; Artificial Intelligence Ethics

Abstract

With the rapid development of Large Language Models (LLMs), research on their cultural biases has gained increasing academic attention, though studies focusing on regional stereotypes remain relatively scarce. This study examines the Doubao v1.6 model using an experimental approach, instructing it to complete stories from the perspectives of “intimacy formation” and “social stratification” to investigate whether it exhibits regional stereotypes, how these are manifested, and how the public can identify and mitigate their influence. The results reveal that Doubao demonstrates regional stereotypes across multiple dimensions—including economic conditions, personality traits, family circumstances, living habits, cultural customs, career choices, and education levels—with more pronounced biases appearing in multi-region scenarios such as “blind date” stories and “job hunting” stories. The writing style of generated content also reflects regional biases. This study validates the existence of regional stereotypes in LLMs and offers methodological insights for future research. It also calls for public awareness and vigilance regarding this issue.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yanze Shi
PY  - 2026
DA  - 2026/03/26
TI  - Examining Regional Stereotypes in Doubao v1.6: A Story Completion Study
BT  - Proceeding of 2025 8th International Conference on Humanities Education and Social Sciences (ICHESS 2025)
PB  - Atlantis Press
SP  - 1197
EP  - 1206
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-551-5_129
DO  - 10.2991/978-2-38476-551-5_129
ID  - Shi2026
ER  -