Explaining Explanations in Probabilistic Logic Programming
This work tackles the challenge of improving explanation quality in transparent AI models like PLP, which is incremental as it builds on existing PLP frameworks.
The paper addresses the problem of generating understandable explanations for probabilistic logic programming (PLP) queries by introducing a new query-driven inference mechanism that uses proof trees and choice expressions to produce comprehensible justifications with a causal structure.
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.