Research

Paper

AI LLM February 27, 2026

ReasonX: Declarative Reasoning on Explanations

Authors

Laura State, Salvatore Ruggieri, Franco Turini

Abstract

Explaining opaque Machine Learning (ML) models has become an increasingly important challenge. However, current eXplanation in AI (XAI) methods suffer several shortcomings, including insufficient abstraction, limited user interactivity, and inadequate integration of symbolic knowledge. We propose ReasonX, an explanation tool based on expressions (or, queries) in a closed algebra of operators over theories of linear constraints. ReasonX provides declarative and interactive explanations for decision trees, which may represent the ML models under analysis or serve as global or local surrogate models for any black-box predictor. Users can express background or common sense knowledge as linear constraints. This allows for reasoning at multiple levels of abstraction, ranging from fully specified examples to under-specified or partially constrained ones. ReasonX leverages Mixed-Integer Linear Programming (MILP) to reason over the features of factual and contrastive instances. We present here the architecture of ReasonX, which consists of a Python layer, closer to the user, and a Constraint Logic Programming (CLP) layer, which implements a meta-interpreter of the query algebra. The capabilities of ReasonX are demonstrated through qualitative examples, and compared to other XAI tools through quantitative experiments.

Metadata

arXiv ID: 2602.23810
Provider: ARXIV
Primary Category: cs.CY
Published: 2026-02-27
Fetched: 2026-03-02 06:04

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.23810v1</id>\n    <title>ReasonX: Declarative Reasoning on Explanations</title>\n    <updated>2026-02-27T08:50:02Z</updated>\n    <link href='https://arxiv.org/abs/2602.23810v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.23810v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Explaining opaque Machine Learning (ML) models has become an increasingly important challenge. However, current eXplanation in AI (XAI) methods suffer several shortcomings, including insufficient abstraction, limited user interactivity, and inadequate integration of symbolic knowledge. We propose ReasonX, an explanation tool based on expressions (or, queries) in a closed algebra of operators over theories of linear constraints. ReasonX provides declarative and interactive explanations for decision trees, which may represent the ML models under analysis or serve as global or local surrogate models for any black-box predictor. Users can express background or common sense knowledge as linear constraints. This allows for reasoning at multiple levels of abstraction, ranging from fully specified examples to under-specified or partially constrained ones. ReasonX leverages Mixed-Integer Linear Programming (MILP) to reason over the features of factual and contrastive instances. We present here the architecture of ReasonX, which consists of a Python layer, closer to the user, and a Constraint Logic Programming (CLP) layer, which implements a meta-interpreter of the query algebra. The capabilities of ReasonX are demonstrated through qualitative examples, and compared to other XAI tools through quantitative experiments.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CY'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-02-27T08:50:02Z</published>\n    <arxiv:primary_category term='cs.CY'/>\n    <author>\n      <name>Laura State</name>\n    </author>\n    <author>\n      <name>Salvatore Ruggieri</name>\n    </author>\n    <author>\n      <name>Franco Turini</name>\n    </author>\n  </entry>"
}