In the paper they introduce an ethics datasets and test GPT-3 and other models on it. Finding out how well models do at different kinds of morality. It's a small but important step towards aligning AI with human values, and the findings and dataset are very interesting.
Abstract:
We show how to assess a language model's knowledge of basic concepts of morality. We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality. Models predict widespread moral judgments about diverse text scenarios. This requires connecting physical and social world knowledge to value judgements, a capability that may enable us to filter out needlessly inflammatory chatbot outputs or eventually regularize open-ended reinforcement learning agents. With the ETHICS dataset, we find that current language models have a promising but incomplete understanding of basic ethical knowledge. Our work shows that progress can be made on machine ethics today, and it provides a steppingstone toward AI that is aligned with human values.
