Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aldahoul, Nouar, Ibrahim, Hazem, Varvello, Matteo, Kaufman, Aaron, Rahwan, Talal, Zaki, Yasir
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912364350144512
author Aldahoul, Nouar
Ibrahim, Hazem
Varvello, Matteo
Kaufman, Aaron
Rahwan, Talal
Zaki, Yasir
author_facet Aldahoul, Nouar
Ibrahim, Hazem
Varvello, Matteo
Kaufman, Aaron
Rahwan, Talal
Zaki, Yasir
contents Large Language Models (LLMs) are a transformational technology, fundamentally changing how people obtain information and interact with the world. As people become increasingly reliant on them for an enormous variety of tasks, a body of academic research has developed to examine these models for inherent biases, especially political biases, often finding them small. We challenge this prevailing wisdom. First, by comparing 31 LLMs to legislators, judges, and a nationally representative sample of U.S. voters, we show that LLMs' apparently small overall partisan preference is the net result of offsetting extreme views on specific topics, much like moderate voters. Second, in a randomized experiment, we show that LLMs can promulgate their preferences into political persuasiveness even in information-seeking contexts: voters randomized to discuss political issues with an LLM chatbot are as much as 5 percentage points more likely to express the same preferences as that chatbot. Contrary to expectations, these persuasive effects are not moderated by familiarity with LLMs, news consumption, or interest in politics. LLMs, especially those controlled by private companies or governments, may become a powerful and targeted vector for political influence.
format Preprint
id arxiv_https___arxiv_org_abs_2505_04171
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts
Aldahoul, Nouar
Ibrahim, Hazem
Varvello, Matteo
Kaufman, Aaron
Rahwan, Talal
Zaki, Yasir
Computers and Society
Computation and Language
Large Language Models (LLMs) are a transformational technology, fundamentally changing how people obtain information and interact with the world. As people become increasingly reliant on them for an enormous variety of tasks, a body of academic research has developed to examine these models for inherent biases, especially political biases, often finding them small. We challenge this prevailing wisdom. First, by comparing 31 LLMs to legislators, judges, and a nationally representative sample of U.S. voters, we show that LLMs' apparently small overall partisan preference is the net result of offsetting extreme views on specific topics, much like moderate voters. Second, in a randomized experiment, we show that LLMs can promulgate their preferences into political persuasiveness even in information-seeking contexts: voters randomized to discuss political issues with an LLM chatbot are as much as 5 percentage points more likely to express the same preferences as that chatbot. Contrary to expectations, these persuasive effects are not moderated by familiarity with LLMs, news consumption, or interest in politics. LLMs, especially those controlled by private companies or governments, may become a powerful and targeted vector for political influence.
title Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts
topic Computers and Society
Computation and Language
url https://arxiv.org/abs/2505.04171