# Model Agnostic Multilevel Explanations

arXiv: https://arxiv.org/abs/2003.06005 · HTML: https://mlsanity.com/paper/2003.06005/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2020.

## Built on by (most cited first, 24 of 24)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations](https://mlsanity.com/paper/2210.11584/) (2022)
- [On the Computational Intelligibility of Boolean Classifiers](https://mlsanity.com/paper/2104.06172/) (2021)
- [Self-Interpretable Time Series Prediction with Counterfactual Explanations](https://mlsanity.com/paper/2306.06024/) (2023)
- [Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View](https://mlsanity.com/paper/2112.02625/) (2021)
- [Let the CAT out of the bag: Contrastive Attributed explanations for Text](https://mlsanity.com/paper/2109.07983/) (2021)
- [Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models](https://mlsanity.com/paper/2403.07733/) (2024)
- [Incremental XAI: Memorable Understanding of AI with Incremental Explanations](https://mlsanity.com/paper/2404.06733/) (2024)
- [Unifying Perspectives: Plausible Counterfactual Explanations on Global, Group-wise, and Local Levels](https://mlsanity.com/paper/2405.17642/) (2024)
- [Explaining Anomalies using Denoising Autoencoders for Financial Tabular Data](https://mlsanity.com/paper/2209.10658/) (2022)
- [Trust Regions for Explanations via Black-Box Probabilistic Certification](https://mlsanity.com/paper/2402.11168/) (2024)
- [Extending LIME for Business Process Automation](https://mlsanity.com/paper/2108.04371/) (2021)
- [CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions](https://mlsanity.com/paper/2506.05586/) (2025)
- [Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners](https://mlsanity.com/paper/2202.01153/) (2022)
- [How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?](https://mlsanity.com/paper/2310.18496/) (2023)
- [Explaining Predictions by Characteristic Rules](https://mlsanity.com/paper/2405.21003/) (2024)
- [Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning](https://mlsanity.com/paper/2201.12143/) (2022)
- [Adaptive Zeroth-Order Optimisation of Nonconvex Composite Objectives](https://mlsanity.com/paper/2208.04579/) (2022)
- [Gradient-free Post-hoc Explainability Using Distillation Aided Learnable Approach](https://mlsanity.com/paper/2409.11123/) (2024)
- [Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations](https://mlsanity.com/paper/2210.08902/) (2022)
- [Adaptive Stochastic Optimisation of Nonconvex Composite Objectives](https://mlsanity.com/paper/2211.11710/) (2022)
- [Transferable XAI: Relating Understanding Across Domains with Explanation Transfer](https://mlsanity.com/paper/2602.13675/) (2026)

## Abstract (arXiv)

In recent years, post-hoc local instance-level and global dataset-level explainability of black-box models has received a lot of attention. Much less attention has been given to obtaining insights at intermediate or group levels, which is a need outlined in recent works that study the challenges in realizing the guidelines in the General Data Protection Regulation (GDPR). In this paper, we propose a meta-method that, given a typical local explainability method, can build a multilevel explanation tree. The leaves of this tree correspond to the local explanations, the root corresponds to the global explanation, and intermediate levels correspond to explanations for groups of data points that it automatically clusters. The method can also leverage side information, where users can specify points for which they may want the explanations to be similar. We argue that such a multilevel structure can also be an effective form of communication, where one could obtain few explanations that characterize the entire dataset by considering an appropriate level in our explanation tree. Explanations for novel test points can be cost-efficiently obtained by associating them with the closest training points. When the local explainability technique is generalized additive (viz. LIME, GAMs), we develop a fast approximate algorithm for building the multilevel tree and study its convergence behavior. We validate the effectiveness of the proposed technique based on two human studies -- one with experts and the other with non-expert users -- on real world datasets, and show that we produce high fidelity sparse explanations on several other public datasets.