Salvato in:
Dettagli Bibliografici
Autori principali: Gopinadh, M P V S, Sindhu, Kappara Lakshmi, P, Soma Sekhar Pandu Ranga Raju, Swarna, Yesaswini
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.16349
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911393394982912
author Gopinadh, M P V S
Sindhu, Kappara Lakshmi
P, Soma Sekhar Pandu Ranga Raju
Swarna, Yesaswini
author_facet Gopinadh, M P V S
Sindhu, Kappara Lakshmi
P, Soma Sekhar Pandu Ranga Raju
Swarna, Yesaswini
contents This study investigates regional bias in large language models (LLMs), an emerging concern in AI fairness and global representation. We evaluate ten prominent LLMs: GPT-3.5, GPT-4o, Gemini 1.5 Flash, Gemini 1.0 Pro, Claude 3 Opus, Claude 3.5 Sonnet, Llama 3, Gemma 7B, Mistral 7B, and Vicuna-13B using a dataset of 100 carefully designed prompts that probe forced-choice decisions between regions under contextually neutral scenarios. We introduce FAZE, a prompt-based evaluation framework that measures regional bias on a 10-point scale, where higher scores indicate a stronger tendency to favor specific regions. Experimental results reveal substantial variation in bias levels across models, with GPT-3.5 exhibiting the highest bias score (9.5) and Claude 3.5 Sonnet scoring the lowest (2.5). These findings indicate that regional bias can meaningfully undermine the reliability, fairness, and inclusivity of LLM outputs in real-world, cross-cultural applications. This work contributes to AI fairness research by highlighting the importance of inclusive evaluation frameworks and systematic approaches for identifying and mitigating geographic biases in language models.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16349
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Regional Bias in Large Language Models
Gopinadh, M P V S
Sindhu, Kappara Lakshmi
P, Soma Sekhar Pandu Ranga Raju
Swarna, Yesaswini
Computation and Language
Artificial Intelligence
This study investigates regional bias in large language models (LLMs), an emerging concern in AI fairness and global representation. We evaluate ten prominent LLMs: GPT-3.5, GPT-4o, Gemini 1.5 Flash, Gemini 1.0 Pro, Claude 3 Opus, Claude 3.5 Sonnet, Llama 3, Gemma 7B, Mistral 7B, and Vicuna-13B using a dataset of 100 carefully designed prompts that probe forced-choice decisions between regions under contextually neutral scenarios. We introduce FAZE, a prompt-based evaluation framework that measures regional bias on a 10-point scale, where higher scores indicate a stronger tendency to favor specific regions. Experimental results reveal substantial variation in bias levels across models, with GPT-3.5 exhibiting the highest bias score (9.5) and Claude 3.5 Sonnet scoring the lowest (2.5). These findings indicate that regional bias can meaningfully undermine the reliability, fairness, and inclusivity of LLM outputs in real-world, cross-cultural applications. This work contributes to AI fairness research by highlighting the importance of inclusive evaluation frameworks and systematic approaches for identifying and mitigating geographic biases in language models.
title Regional Bias in Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.16349