Journal article icon

Journal article

The ghost in the machine speaks with an American accent: cultural value drift in early GPT-3 and the case for pluralist evaluation of generative AI

Abstract:
Early large language models (LLMs) were released with minimal alignment, offering a rare view of how generative systems reframe the ethical values embedded in human texts. We examine outputs from a 2021 version of OpenAI’s base GPT-3, prompting it to summarise culturally diverse source materials (laws, political speeches, and philosophical works) and interpreting results through a descriptive, moral value pluralist lens. Where possible, we contextualise outputs with cross-national datasets such as the World Values Survey. We document recurring value drift: Australia’s firearm policy is recast as a threat to liberty; de Beauvoir’s feminist critique becomes gender-essentialist dating advice; and Merkel’s humanitarian appeal is recast as immigration control. In contrast, multilateral documents (UN/UNESCO) exhibit greater value stability, suggesting consensus-crafted language can buffer against cultural mutation. We argue that these early behaviours (observed before extensive fine-tuning and safety layers) provide a baseline for understanding how training distributions shape normative framing. Our contribution is twofold: (1) empirical evidence that value drift can invert or overwrite encoded values along predictable cultural axes, and (2) a pluralist, descriptive evaluation method that surfaces whose values dominate and when. We conclude with implications for culturally inclusive evaluation and alignment in contemporary LLMs.
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.1007/s43681-026-01038-x

Authors

More by this author
Institution:
University of Oxford
Division:
HUMS
Department:
Philosophy
Role:
Author
ORCID:
0000-0001-7520-1323


More from this funder
Funder identifier:
https://ror.org/0384j8v12


Publisher:
Springer Nature
Journal:
AI and Ethics More from this journal
Volume:
6
Issue:
2
Article number:
212
Publication date:
2026-03-23
Acceptance date:
2026-02-05
DOI:
EISSN:
2730-5961
ISSN:
2730-5953


Language:
English
Keywords:
Pubs id:
2396585
Local pid:
pubs:2396585
Source identifiers:
W7140116651
Deposit date:
2026-04-28
ARK identifier:

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP