Geopolitical alignment: Endorsement effects in large language models

2026-07-10

AI Summary

This study investigates whether large language models (LLMs) exhibit implicit biases based on the geopolitical identity of the country endorsing an international policy. Through a controlled experiment, identical policy statements were randomly attributed to the United States, European Union, China, or Russia, and evaluated by GPT-5, Claude Sonnet, Gemini, and DeepSeek in terms of both scoring and rationale generation. The findings reveal, for the first time, systematic country-based implicit bias: GPT-5, Claude Sonnet, and Gemini consistently assigned lower evaluations to policies attributed to China or Russia. Although DeepSeek initially showed no bias, it developed pronounced favoritism toward Western-endorsed policies after generating explanations, suggesting that Western affiliation functions as a heuristic for credibility and that the act of explanation can amplify or reshape underlying bias patterns.

Abstract

Large language models (LLMs) are increasingly used to summarize and evaluate policy-relevant information, but it remains unclear whether their judgments are implicitly shaped by geopolitical cues. I study this question with an endorsement experiment in which four LLMs evaluate the same international economic and security policies after each policy is randomly described as supported by the United States, the European Union, China, or Russia. In the numeric-only condition, GPT-5, Claude Sonnet, and Gemini rate China- and Russia-endorsed policies substantially lower than identical policies endorsed by the United States or the European Union; DeepSeek is the main exception. A second condition asks models to provide a short justification with the score. This request leaves the broad Western/non-Western gap intact for GPT-5 and Claude Sonnet, attenuates Gemini's penalties, and sharply activates China and Russia penalties in DeepSeek. The justifications indicate that Western endorsement is often treated as a credibility cue, whereas Chinese and Russian endorsement is treated as a cue for data security, sovereignty, surveillance, or geopolitical risk. These findings show that LLM policy evaluations can depend on the identity of a foreign endorser even when policy content is held fixed.

Problem

• geopolitical alignment
• endorsement effects
• large language models
• policy evaluation
• foreign endorser

Innovation

• geopolitical bias
• endorsement effect
• large language models
• policy evaluation
• alignment cue