[Department of Political Science and International Relations 10-10 Project]
SEOUL POLITICAL SCIENCE AND INTERNATIONAL RELATIONS RESEARCH SYMPOSIUM (SPIRS) SERIES
Lecture Topic: Large Language Models Exhibit Extreme Partisan Preferences that Influence Political Preferences
Speaker: Aaron R. Kaufman (Assistant Professor of Political Science, NYU Abu Dhabi)
Date: May 20, 2025 15:00–16:30
Venue: Faculty Conference Room, College of Social Sciences (Building 16, Room 312)
- The lecture will be conducted entirely in English.
- No pre-registration is required; open to all attendees.
- The event is in-person only (no online streaming).
- For presentation materials, please contact the organizer.
Contact: Political Science and International Relations 10-10 Project Assistant(lveronica93@snu.ac.kr)
Authors: Nouar Aldahoul, Hazem Ibrahim, Matteo Varvello, Aaron R. Kaufman, Talal Rahwan, and Yasir Zaki
Abstract: 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 25 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.