mlsanityData to 7 Oct 2026

Declarative Reasoning on Explanations Using Constraint Logic Programming

arXiv 2309.00422 ↗First posted 1 Sep 2023cs.AI cs.CY cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Explaining opaque Machine Learning (ML) models is an increasingly relevant problem. Current explanation in AI (XAI) methods suffer several shortcomings, among others an insufficient incorporation of background knowledge, and a lack of abstraction and interactivity with the user. We propose REASONX, an explanation method based on Constraint Logic Programming (CLP). REASONX can provide declarative, interactive explanations for decision trees, which can be the ML models under analysis or global/local surrogate models of any black-box model. Users can express background or common sense knowledge using linear constraints and MILP optimization over features of factual and contrastive instances, and interact with the answer constraints at different levels of abstraction through constraint projection. We present here the architecture of REASONX, which consists of a Python layer, closer to the user, and a CLP layer. REASONX's core execution engine is a Prolog meta-program with declarative semantics in terms of logic theories.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 52 references that are in the map. First posted on arXiv 1 Sep 2023.

Builds on

19 of 52 references.

References · 19

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  3. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  4. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  5. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  6. 2018Explaining Explanations in AIcited by 136
  7. 2020A survey of algorithmic recourse: definitions, formulations, solutions, and prospectscited by 118
  8. 2019Efficient Search for Diverse Coherent Explanationscited by 111
  9. 2020Inductive logic programming at 30: a new introductioncited by 83
  10. 2020One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparencycited by 64
  11. 2018RuleMatrix: Visualizing and Understanding Classifiers with Rulescited by 62
  12. 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
7 more
  1. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  2. 2021GLocalX -- From Local to Global Explanations of Black Box AI Modelscited by 48
  3. 2022Fifty Years of Prolog and Beyondcited by 15
  4. 2020Declarative Approaches to Counterfactual Explanations for Classificationcited by 14
  5. 2021Explainable Machine Learning with Prior Knowledge: An Overviewcited by 14
  6. 2020Abduction and Argumentation for Explainable Machine Learning: A Position Surveycited by 6
  7. 2023Reason to explain: Interactive contrastive explanations (REASONX)cited by 2

Built on by

Not cited yet.