A System for Explainable Answer Set Programming
This work provides a system for explainable AI in ASP, addressing the need for interpretability in logic programming, though it is incremental as it builds on existing ASP frameworks.
The authors tackled the problem of generating explanations for Answer Set Programming (ASP) programs by introducing xclingo, a tool that uses annotations to trace rules and derived atoms, resulting in the ability to construct derivation trees with textual explanations while maintaining compatibility with standard ASP solvers.
We present xclingo, a tool for generating explanations from ASP programs annotated with text and labels. These annotations allow tracing the application of rules or the atoms derived by them. The input of xclingo is a markup language written as ASP comment lines, so the programs annotated in this way can still be accepted by a standard ASP solver. xclingo translates the annotations into additional predicates and rules and uses the ASP solver clingo to obtain the extension of those auxiliary predicates. This information is used afterwards to construct derivation trees containing textual explanations. The language allows selecting which atoms to explain and, in its turn, which atoms or rules to include in those explanations. We illustrate the basic features through a diagnosis problem from the literature.