Most General Explanations of Tree Ensembles (Extended Version)

TL;DR

This paper introduces a method to find the most general abductive explanations for AI decisions, covering the largest input space while remaining accurate, thereby improving the interpretability and trustworthiness of AI systems.

Contribution

It proposes a novel approach to identify the most general explanations for tree ensemble decisions, enhancing the interpretability of AI models by covering broader input regions.

Findings

Most general explanations cover larger input spaces.

The method guarantees correctness of explanations.

Applicable to tree ensemble models.

Abstract

Explainable Artificial Intelligence (XAI) is critical for attaining trust in the operation of AI systems. A key question of an AI system is ``why was this decision made this way''. Formal approaches to XAI use a formal model of the AI system to identify abductive explanations. While abductive explanations may be applicable to a large number of inputs sharing the same concrete values, more general explanations may be preferred for numeric inputs. So-called inflated abductive explanations give intervals for each feature ensuring that any input whose values fall withing these intervals is still guaranteed to make the same prediction. Inflated explanations cover a larger portion of the input space, and hence are deemed more general explanations. But there can be many (inflated) abductive explanations for an instance. Which is the best? In this paper, we show how to find a most general abductive explanation for an AI decision. This explanation covers as much of the input space as possible, while still being a correct formal explanation of the model's behaviour. Given that we only want to give a human one explanation for a decision, the most general explanation gives us the explanation with the broadest applicability, and hence the one most likely to seem sensible. (The paper has been accepted at IJCAI2025 conference.)