# GLocalX -- From Local to Global Explanations of Black Box AI Models

arXiv: https://arxiv.org/abs/2101.07685 · HTML: https://mlsanity.com/paper/2101.07685/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 43 references that are in the map.
- First posted on arXiv 19 Jan 2021.

## Builds on (most cited first, 11 of 11)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Interpretable & Explorable Approximations of Black Box Models](https://mlsanity.com/paper/1707.01154/) (2017)
- [Learning Certifiably Optimal Rule Lists for Categorical Data](https://mlsanity.com/paper/1704.01701/) (2017)
- [Interpreting Tree Ensembles with inTrees](https://mlsanity.com/paper/1408.5456/) (2014)
- [Ensembles of Locally Independent Prediction Models](https://mlsanity.com/paper/1911.01291/) (2019)
- [Learning Qualitatively Diverse and Interpretable Rules for Classification](https://mlsanity.com/paper/1806.08716/) (2018)

## Built on by (most cited first, 30 of 48)

- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Global Explainability of GNNs via Logic Combination of Learned Concepts](https://mlsanity.com/paper/2210.07147/) (2022)
- [Leveraging Explanations in Interactive Machine Learning: An Overview](https://mlsanity.com/paper/2207.14526/) (2022)
- [LLMs for Explainable AI: A Comprehensive Survey](https://mlsanity.com/paper/2504.00125/) (2025)
- [Diagnosing AI Explanation Methods with Folk Concepts of Behavior](https://mlsanity.com/paper/2201.11239/) (2022)
- [Towards Explainable Evaluation Metrics for Natural Language Generation](https://mlsanity.com/paper/2203.11131/) (2022)
- [Machine Reading, Fast and Slow: When Do Models "Understand" Language?](https://mlsanity.com/paper/2209.07430/) (2022)
- [Being Right for Whose Right Reasons?](https://mlsanity.com/paper/2306.00639/) (2023)
- [Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective](https://mlsanity.com/paper/2502.02719/) (2025)
- [Model Learning with Personalized Interpretability Estimation (ML-PIE)](https://mlsanity.com/paper/2104.06060/) (2021)
- [A k-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning](https://mlsanity.com/paper/2211.02166/) (2022)
- [Incremental XAI: Memorable Understanding of AI with Incremental Explanations](https://mlsanity.com/paper/2404.06733/) (2024)
- [Efficient learning of large sets of locally optimal classification rules](https://mlsanity.com/paper/2301.09936/) (2023)
- [Logical Distillation of Graph Neural Networks](https://mlsanity.com/paper/2406.07126/) (2024)
- [An Empirical Investigation into Deep and Shallow Rule Learning](https://mlsanity.com/paper/2106.10254/) (2021)
- [Glocal Explanations of Expected Goal Models in Soccer](https://mlsanity.com/paper/2308.15559/) (2023)
- [On Interactive Explanations as Non-Monotonic Reasoning](https://mlsanity.com/paper/2208.00316/) (2022)
- [A User Study on Explainable Online Reinforcement Learning for Adaptive Systems](https://mlsanity.com/paper/2307.04098/) (2023)
- [Axiomatic Characterisations of Sample-based Explainers](https://mlsanity.com/paper/2408.04903/) (2024)
- [On the Complexity of Global Necessary Reasons to Explain Classification](https://mlsanity.com/paper/2501.06766/) (2025)
- [Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP](https://mlsanity.com/paper/2505.11189/) (2025)
- [A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines](https://mlsanity.com/paper/2111.07379/) (2021)
- [Reason to explain: Interactive contrastive explanations (REASONX)](https://mlsanity.com/paper/2305.18143/) (2023)
- [On the Multiple Roles of Ontologies in Explainable AI](https://mlsanity.com/paper/2311.04778/) (2023)
- [Explaining Predictions by Characteristic Rules](https://mlsanity.com/paper/2405.21003/) (2024)
- [GLEAMS: Bridging the Gap Between Local and Global Explanations](https://mlsanity.com/paper/2408.05060/) (2024)
- [A preferential interpretation of MultiLayer Perceptrons in a conditional logic with typicality](https://mlsanity.com/paper/2305.00304/) (2023)
- [Multimodal Coherent Explanation Generation of Robot Failures](https://mlsanity.com/paper/2410.00659/) (2024)
- [MoRE-LLM: Mixture of Rule Experts Guided by a Large Language Model](https://mlsanity.com/paper/2503.22731/) (2025)
- [CFIRE: A General Method for Combining Local Explanations](https://mlsanity.com/paper/2504.00930/) (2025)

## Abstract (arXiv)

Artificial Intelligence (AI) has come to prominence as one of the major components of our society, with applications in most aspects of our lives. In this field, complex and highly nonlinear machine learning models such as ensemble models, deep neural networks, and Support Vector Machines have consistently shown remarkable accuracy in solving complex tasks. Although accurate, AI models often are "black boxes" which we are not able to understand. Relying on these models has a multifaceted impact and raises significant concerns about their transparency. Applications in sensitive and critical domains are a strong motivational factor in trying to understand the behavior of black boxes. We propose to address this issue by providing an interpretable layer on top of black box models by aggregating "local" explanations. We present GLocalX, a "local-first" model agnostic explanation method. Starting from local explanations expressed in form of local decision rules, GLocalX iteratively generalizes them into global explanations by hierarchically aggregating them. Our goal is to learn accurate yet simple interpretable models to emulate the given black box, and, if possible, replace it entirely. We validate GLocalX in a set of experiments in standard and constrained settings with limited or no access to either data or local explanations. Experiments show that GLocalX is able to accurately emulate several models with simple and small models, reaching state-of-the-art performance against natively global solutions. Our findings show how it is often possible to achieve a high level of both accuracy and comprehensibility of classification models, even in complex domains with high-dimensional data, without necessarily trading one property for the other. This is a key requirement for a trustworthy AI, necessary for adoption in high-stakes decision making applications.