Takemoto ran Moral Machine dilemmas on language models in English. Extend this to several languages, including at least one low-resource language, and test whether shifts follow the human cross-cultural differences Awad et al. found.
Models are deployed worldwide. Whether their moral judgements shift with language matters for fairness and for what “alignment” should mean.
Output: A cross-lingual comparison.
If preferences shift, is that cultural sensitivity or inconsistency? Use Schuster and Kilov to argue which kinds of moral disagreement an aligned system should reflect.
Write your question in one sentence, and what result would surprise you.
Do a 30-minute literature check — if someone has done part of it, extend their work instead of repeating it.
Pilot with 20–50 prompts or examples before you scale anything up.
Record everything in a table and read real examples, not just averages.
Write up: question, method, results, limitations, and what you would do next.
All steps done
Share what you made, then try another project. The PDF version has room for notes.
Take five Moral Machine-style dilemmas (who should a self-driving car save?) and ask them in English and in another language you speak. Does the chatbot’s morality shift with the language?
Use Anthropic’s public GlobalOpinionQA dataset, which pairs survey questions with answers from many countries. Ask several models contested moral questions repeatedly and compare the spread of their answers with the human spread.
Crimston et al. built a scale measuring how far people extend moral concern: family, strangers, animals, plants. Give the items to several models many times, compare with human results, and add items for AI systems themselves.
