My colleagues and Iat Purdue University have uncovered a significant imbalance in the human values embedded inAIsystems.
The systems were predominantly oriented toward information and utility values and less toward prosocial, well-being and civic values.
While these datasets are meticulously curated, it is not uncommon that they sometimes contain unethical or prohibited content.
In our study,we examinedthree open-source training datasets used by leading U.S. AI companies.
Our model allowed us to examine the AI companies datasets.
Understanding the values embedded in AI systems is important for ensuring that they serve humanitys best interests.
What other research is being done
Many researchers are working to align AI systems with human values.
Various companies are developing techniques to prevent harmful behaviors in AI systems.
