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 steer 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 ability to predict basic human ethical judgements. 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.
Latest posts by Ryan Watkins (see all)
- Synergizing Human-AI Agency: A Guide of 23 Heuristics for Service Co-Creation with LLM-Based Agents - December 1, 2023
- AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction [imputation] - November 29, 2023
- Enhancing Human Persuasion With Large Language Models - November 29, 2023