서울대학교

[정치외교학부 10-10 사업단]

SEOUL POLITICAL SCIENCE AND INTERNATIONAL RELATIONS RESEARCH SYMPOSIUM (SPIRS) SERIES

Large Language Models Exhibit Extreme Partisan Preferences that Influence Political Preferences

AARON R. KAUFMAN (Assistant Professor of Political Science, New York University (NYU) Abu Dhabi)

일시: 2025년 5월 20일 15:00-16:30
장소: 사회과학대학 교수대회의실(16동 312호)
* 행사는 모두 영어로 진행됩니다.
* 사전 신청 없이 참석 가능하며, 오프라인으로만 진행됩니다.
* 발표 자료 희망시 문의처로 연락 바랍니다.

문의처: 정치외교학부 10-10 사업조교 (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.