On Validating, Repairing and Refining Heuristic ML Explanations

Explainable Artificial Intelligence (XAI) aims to help human decision makers in understanding the operation of complex AI models. However, many XAI solutions, based on non-symbolic methods, offer no formal guarantees and can produce erroneous results. In contrast, logic-based XAI guarantees the rigor of computed explanations, and this is paramount in high-stakes uses of AI. This talk overviews several flagship applications of Boolean satisfiability (SAT) solvers in reasoning about logic-based explanations.

Interpretability ML methods Systems & infrastructure cs.LG cs.AI cs.LO Explainable Artificial Intelligence (XAI)Machine Learning and Data Classification Scientific Computing and Data Management

Paper

Similar papers

Logic-Based Explainability: Past, Present & FutureJoao Marques-Silva2024 · arXiv (Cornell University) In Library

Logic-Based Explainability: Past, Present and FutureJoão Marques‐Silva2024 · Lecture notes in computer science In Library

Explainable Logic-Based ArgumentationOfer Arieli, AnneMarie Borg, Matthis Hesse et al.2022 · Frontiers in artificial intelligence and applications In Library

Explainable Artificial Intelligence Using Expressive Boolean FormulasGili Rosenberg, J. Kyle Brubaker, Martin J. A. Schuetz et al.2023 · Machine Learning and Knowledge Extraction In Library

Towards symbolic XAI — explanation through human understandable logical relationships between featuresThomas Schnake, Farnoush Rezaei Jafari, Jonas Lederer et al.2025 · Information Fusion In Library

On Computing Probabilistic Explanations for Decision TreesMarcelo Arenas, Pablo Barceló, Alexander Kozachinskiy et al.2025 · Journal of Artificial Intelligence Research · 0 citations In Library

Explainable AI using expressive Boolean formulasGili Rosenberg, J. Kyle Brubaker, Martin J. A. Schuetz et al.2023 · arXiv (Cornell University) · 15 citations In Library

On Computing Probabilistic Explanations for Decision TreesMarcelo Arenas, Pablo Barceló, Miguel Romero et al.2022 · arXiv (Cornell University) · 54 citations In Library

Rule-based Explainable Artificial IntelligenceSinem Akyol2023 In Library

Explainable AI: Bridging the Gap between Machine Learning Models and Human UnderstandingRajiv Avacharmal2024 · Journal of Informatics Education and Research In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal