On Conforming and Conflicting Values
This work addresses a theoretical problem in value classification for researchers in ethics or AI alignment, but it appears incremental as it builds on existing concepts without introducing new methods or data.
The paper tackles the classification of values into conflicting and inherently conflicting types, arguing that the latter are independent of actions, and demonstrates how this distinction enables checking the consistency of a value set and its conflicts with other sets.
Values are things that are important to us. Actions activate values - they either go against our values or they promote our values. Values themselves can either be conforming or conflicting depending on the action that is taken. In this short paper, we argue that values may be classified as one of two types - conflicting and inherently conflicting values. They are distinguished by the fact that the latter in some sense can be thought of as being independent of actions. This allows us to do two things: i) check whether a set of values is consistent and ii) check whether it is in conflict with other sets of values.