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.
|
|
Professor at George Washington University
I am a Professor with Human-Technology Collaboration and Educational Technology programs at George Washington University in Washington DC. I have written 12 books and more than 100 articles, and I co-host of the Parsing Science podcast where scientists tell the stories behind their research. I am also the developer of the WeShareScience.com online platform for sharing research videos, and SciencePods.com where researchers can create free podcasts about their science. My research interests include human interactions with intelligent machines, needs, needs assessments, and instructional design.
Latest posts by Ryan Watkins (see all)
- POTATO: The Portable Text Annotation Tool - March 27, 2023
- Decision-aid or Controller? Steering Human Decision Makers with Algorithms - March 27, 2023
- Human Uncertainty in Concept-Based AI Systems - March 24, 2023