Most General Explanations of Tree Ensembles (Extended Version)

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Izza, Yacine, Ignatiev, Alexey, Rubin, Sasha, Marques-Silva, Joao, Stuckey, Peter J.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916745016508416
author Izza, Yacine
Ignatiev, Alexey
Rubin, Sasha
Marques-Silva, Joao
Stuckey, Peter J.
author_facet Izza, Yacine
Ignatiev, Alexey
Rubin, Sasha
Marques-Silva, Joao
Stuckey, Peter J.
contents 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.)
format Preprint
id arxiv_https___arxiv_org_abs_2505_10991
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Most General Explanations of Tree Ensembles (Extended Version)
Izza, Yacine
Ignatiev, Alexey
Rubin, Sasha
Marques-Silva, Joao
Stuckey, Peter J.
Artificial Intelligence
Machine Learning
Logic in Computer Science
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.)
title Most General Explanations of Tree Ensembles (Extended Version)
topic Artificial Intelligence
Machine Learning
Logic in Computer Science
url https://arxiv.org/abs/2505.10991