“Turning right”? An experimental study on the political value shift in large language models

Yifei Liu, Yuang Panwang and Chao Gu ()
Additional contact information
Yifei Liu: Peking University
Yuang Panwang: Renmin University of China
Chao Gu: Peking University

Palgrave Communications, 2025, vol. 12, issue 1, 1-10

Abstract: Abstract Constructing artificial intelligence that aligns with human values is a crucial challenge, with political values playing a distinctive role among various human value systems. In this study, we adapted the Political Compass Test and combined it with rigorous bootstrapping techniques to create a standardized method for testing political values in AI. This approach was applied to multiple versions of ChatGPT, utilizing a dataset of over 3000 tests to ensure robustness. Our findings reveal that while newer versions of ChatGPT consistently maintain values within the libertarian-left quadrant, there is a statistically significant rightward shift in political values over time, a phenomenon we term a ‘value shift’ in large language models. This shift is particularly noteworthy given the widespread use of LLMs and their potential influence on societal values. Importantly, our study controlled for factors such as user interaction and language, and the observed shifts were not directly linked to changes in training datasets. While this research provides valuable insights into the dynamic nature of value alignment in AI, it also underscores limitations, including the challenge of isolating all external variables that may contribute to these shifts. These findings suggest a need for continuous monitoring of AI systems to ensure ethical value alignment, particularly as they increasingly integrate into human decision-making and knowledge systems.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1057/s41599-025-04465-z Abstract (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:pal:palcom:v:12:y:2025:i:1:d:10.1057_s41599-025-04465-z

Ordering information: This journal article can be ordered from
https://www.nature.com/palcomms/about

DOI: 10.1057/s41599-025-04465-z

Access Statistics for this article

More articles in Palgrave Communications from Palgrave Macmillan
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().