The Ghost in the Machine has an American accent: value conflict in GPT-3

Abstract

The alignment problem in the context of large language models must consider the plurality of human values in our world. Whilst there are many resonant and overlapping values amongst the world’s cultures, there are also many conflicting, yet equally valid, values. It is important to observe which cultural values a model exhibits, particularly when there is a value conflict between input prompts and generated outputs. We discuss how the co- creation of language and cultural value impacts large language models (LLMs). We explore the constitution of the training data for GPT-3 and compare that to the world’s language and internet access demographics, as well as to reported statistical profiles of dominant values in some Nation-states. We stress tested GPT-3 with a range of value-rich texts representing several languages and nations; including some with values orthogonal to dominant US public opinion as reported by the World Values Survey. We observed when values embedded in the input text were mutated in the generated outputs and noted when these conflicting values were more aligned with reported dominant US values. Our discussion of these results uses a moral value pluralism (MVP) lens to better understand these value mutations. Finally, we provide recommendations for how our work may contribute to other current work in the field.

Other Versions

No versions found

Links

PhilArchive

External links

  • This entry has no external links. Add one.
Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

  • Only published works are available at libraries.

Similar books and articles

Value alignment, human enhancement, and moral revolutions.Ariela Tubert & Justin Tiehen - forthcoming - Inquiry: An Interdisciplinary Journal of Philosophy.
Value Capture.Christopher Nguyen - 2024 - Journal of Ethics and Social Philosophy 27 (3).
Challenges of Aligning Artificial Intelligence with Human Values.Margit Sutrop - 2020 - Acta Baltica Historiae Et Philosophiae Scientiarum 8 (2):54-72.

Analytics

Added to PP
2022-05-18

Downloads
234 (#97,416)

6 months
104 (#65,072)

Historical graph of downloads
How can I increase my downloads?

Author Profiles

Citations of this work

No citations found.

Add more citations

References found in this work

Artificial Intelligence, Values, and Alignment.Iason Gabriel - 2020 - Minds and Machines 30 (3):411-437.
Mortal Questions.Thomas Nagel - 1980 - Critica 12 (34):125-133.
The logic of judgments of practise.John Dewey - 1915 - Journal of Philosophy, Psychology and Scientific Methods 12 (19):505-523.

Add more references