# Large language models reflect the ideology of their creators

## TL;DR

This study shows that large language models reflect the political ideologies of their creators, with differences based on region and language.

## Contribution

The study reveals how LLMs from different geopolitical regions and languages exhibit distinct ideological biases.

## Key findings

- LLMs from different regions show disparities in ideological positions.
- U.S. models display normative differences related to progressive values.
- Chinese models show division between international and domestic focus.

## Abstract

Large language models (LLMs) already play an influential role in how humans access information. However, their behavior varies depending on their design, training, and use. We prompt a diverse panel of 19 popular LLMs to describe 3,991 prominent persons with political relevance, and then judge how positively they portray each person. When comparing these assessments, we find disparities in ideological positions between LLMs across different geopolitical regions (Arabic countries, China, Russia, and Western countries), and across different languages (the United Nations’ six official languages). Moreover, among only models from the United States, we find significant normative differences related to progressive values. Among Chinese models, we characterize division between internationally- and domestically-focused models. Our results suggest that the ideological stance of an LLM reflects the worldview of its creators. This poses the risk of political instrumentalization and raises concerns around technological and regulatory efforts aiming to make LLMs ideologically ‘unbiased’.