Is ChatGPT conservative or liberal? A novel approach to assess ideological stances and biases in generative LLMs

Bibliographic Data

ID6445304
AuthorsChristina P Walker (0000-0001-6591-2244, Purdue University West Lafayette), Joan C Timoneda (0000-0001-7057-872X, Purdue University West Lafayette, corresponding author)
Year2025
Pages1-15
Publication date2025-12-03
Open AccessYes
TypeARTICLE
VenuePolitical Science Research and Methods (JOURNAL)
Journal identifiersISSN: 2049-8470 • E-ISSN: 2049-8489
PublisherCambridge University Press (CUP) (PUBLISHER)
DOI10.1017/psrm.2025.10057
OpenAlexW4416942090
LanguageEN
Citations received1
References cited41

Extant work shows that generative AI such as GPT-3.5 and perpetuate social stereotypes and biases. A less explored source of bias is ideology: do GPT models take ideological stances on politically sensitive topics? We develop a novel approach to identify ideological bias and show that it can originate in both the training data and the filtering algorithm. Using linguistic variation across countries with contrasting political attitudes, we evaluate average GPT responses in those languages. GPT output is more conservative in languages conservative societies (polish) and more liberal in languages used in liberal ones (Swedish). These differences persist from GPT-3.5 to GPT-4. We conclude that high-quality, curated training data are essential for reducing bias

Tools

Open DOIOpen Access