Explaining Explanations in Probabilistic Logic Programming

TL;DR

This paper introduces a new approach to generating human-understandable explanations in probabilistic logic programming by labeling proofs with choice expressions, providing clearer causal justifications for queries.

Contribution

It proposes a novel query-driven inference mechanism that labels proof trees with choice expressions, enhancing explanation clarity in probabilistic logic programming.

Findings

Produces comprehensible query justifications with causal structure

Improves explanation relevance by filtering irrelevant choices

Offers a compact representation for sets of choices

Abstract

The emergence of tools based on artificial intelligence has also led to the need of producing explanations which are understandable by a human being. In most approaches, the system is considered a black box, making it difficult to generate appropriate explanations. In this work, though, we consider a setting where models are transparent: probabilistic logic programming (PLP), a paradigm that combines logic programming for knowledge representation and probability to model uncertainty. However, given a query, the usual notion of explanation is associated with a set of choices, one for each random variable of the model. Unfortunately, such a set does not explain why the query is true and, in fact, it may contain choices that are actually irrelevant for the considered query. To improve this situation, we present in this paper an approach to explaining explanations which is based on defining a new query-driven inference mechanism for PLP where proofs are labeled with "choice expressions", a compact and easy to manipulate representation for sets of choices. The combination of proof trees and choice expressions allows us to produce comprehensible query justifications with a causal structure.