Declarative Reasoning on Explanations Using Constraint Logic Programming
This addresses the need for more interactive and knowledge-aware explanations in AI, particularly for users dealing with black-box models, though it appears incremental as it builds on existing explanation methods.
The authors tackled the problem of explaining opaque machine learning models by proposing REASONX, a method based on Constraint Logic Programming that provides declarative, interactive explanations for decision trees or surrogate models, allowing users to incorporate background knowledge through constraints.
Explaining opaque Machine Learning (ML) models is an increasingly relevant problem. Current explanation in AI (XAI) methods suffer several shortcomings, among others an insufficient incorporation of background knowledge, and a lack of abstraction and interactivity with the user. We propose REASONX, an explanation method based on Constraint Logic Programming (CLP). REASONX can provide declarative, interactive explanations for decision trees, which can be the ML models under analysis or global/local surrogate models of any black-box model. Users can express background or common sense knowledge using linear constraints and MILP optimization over features of factual and contrastive instances, and interact with the answer constraints at different levels of abstraction through constraint projection. We present here the architecture of REASONX, which consists of a Python layer, closer to the user, and a CLP layer. REASONX's core execution engine is a Prolog meta-program with declarative semantics in terms of logic theories.