Evaluating Regional Bias in LLMs From Abstract Stereotype to Concrete Social Decision-Making
Not on the map. Why?
Abstract (arXiv)
Regional bias in large language models (LLMs) may shape both perceptions of regional groups and decisions about individuals from different regions. Yet existing studies often examine these manifestations separately, leaving their structure and consequences unclear. We introduce Stereotypes-to-Decisions (S2D), a systematic framework evaluating regional bias from abstract stereotypes to concrete social decisions. Covering all 34 provincial-level administrative regions of China, S2D evaluates six LLMs using stereotype ratings of Warmth (perceived friendliness and trustworthiness) and Competence (perceived capability and intelligence), along with paired-choice tasks across Education, Occupation, and Social Interaction. Results reveal substantial regional differences in regional scores, with considerable agreement across models, especially for Competence and Occupation decisions. Furthermore, these patterns are associated with regional economic and digital development indicators and display mixed human-like stereotypes, with some regions rated highly on one dimension but poorly on the other. They also remain largely stable across Chinese and English prompts. Overall, our findings show that regional bias in LLMs is prevalent, systematic, and consequential, motivating more regionally aware evaluation and mitigation.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 20 references that are in the map. First posted on arXiv 29 Jul 2026.
Builds on
12 of 20 references.
References · 12
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
- 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
- 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
- 2023Generative Language Models Exhibit Social Identity Biasescited by 107
- 2024Large Language Models are Geographically Biasedcited by 91
- 2023Split and Merge: Aligning Position Biases in LLM-based Evaluatorscited by 71
- 2023This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Modelscited by 31
- 2022Geographic and Geopolitical Biases of Language Modelscited by 29
- 2024BanStereoSet: A Dataset to Measure Stereotypical Social Biases in LLMs for Banglacited by 3
- 2026Common to Whom? Regional Cultural Commonsense and LLM Bias in Indiacited by 3
- 2026Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMscited by 3
Built on by
Not cited yet.