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

by   Rebecca L Johnson, et al.

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.


Probing Pre-Trained Language Models for Cross-Cultural Differences in Values

Language embeds information about social, cultural, and political values...

Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values

Many NLP classification tasks, such as sexism/racism detection or toxici...

Knowledge of cultural moral norms in large language models

Moral norms vary across cultures. A recent line of work suggests that En...

Aligning AI With Shared Human Values

We show how to assess a language model's knowledge of basic concepts of ...

AceGPT, Localizing Large Language Models in Arabic

This paper explores the imperative need and methodology for developing a...

What does ChatGPT return about human values? Exploring value bias in ChatGPT using a descriptive value theory

There has been concern about ideological basis and possible discriminati...

Accessibility Across Borders

Since prior work has identified that cultural differences influence user...

Please sign up or login with your details

Forgot password? Click here to reset