# UbiQTree: Uncertainty Quantification in XAI with Tree Ensembles

arXiv: https://arxiv.org/abs/2508.09639 · HTML: https://mlsanity.com/paper/2508.09639/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 96 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Builds on (most cited first, 21 of 21)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Logic Tensor Networks](https://mlsanity.com/paper/2012.13635/) (2020)
- [Explainable deep learning models in medical image analysis](https://mlsanity.com/paper/2005.13799/) (2020)
- [A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME](https://mlsanity.com/paper/2305.02012/) (2023)
- [Explaining Predictive Uncertainty with Information Theoretic Shapley Values](https://mlsanity.com/paper/2306.05724/) (2023)
- [On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results](https://mlsanity.com/paper/2104.08015/) (2021)
- [Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles](https://mlsanity.com/paper/2401.12069/) (2024)
- [RKHS-SHAP: Shapley Values for Kernel Methods](https://mlsanity.com/paper/2110.09167/) (2021)
- [A Nested Model for AI Design and Validation](https://mlsanity.com/paper/2407.16888/) (2024)
- [Comparing interpretability and explainability for feature selection](https://mlsanity.com/paper/2105.05328/) (2021)
- [Uncertainty Propagation in XAI: A Comparison of Analytical and Empirical Estimators](https://mlsanity.com/paper/2504.03736/) (2025)
- [Reducing Aleatoric and Epistemic Uncertainty through Multi-modal Data Acquisition](https://mlsanity.com/paper/2501.18268/) (2025)
- [AI Readiness in Healthcare through Storytelling XAI](https://mlsanity.com/paper/2410.18725/) (2024)
- [Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review](https://mlsanity.com/paper/2407.12058/) (2024)
- [Explaining and visualizing black-box models through counterfactual paths](https://mlsanity.com/paper/2307.07764/) (2023)
- [The Distributional Uncertainty of the SHAP score in Explainable Machine Learning](https://mlsanity.com/paper/2401.12731/) (2024)
- [SHAP-Integrated Convolutional Diagnostic Networks for Feature-Selective Medical Analysis](https://mlsanity.com/paper/2503.08712/) (2025)
- [Surrogate Interpretable Graph for Random Decision Forests](https://mlsanity.com/paper/2506.01988/) (2025)

## Built on by (most cited first, 4 of 4)

- [UbiQVision: Quantifying Uncertainty in XAI for Image Recognition](https://mlsanity.com/paper/2512.20288/) (2025)
- [Reverse Probing: Supervised Token-level Uncertainty Quantification for Large Language Models in Clinical Text](https://mlsanity.com/paper/2605.28740/) (2026)
- [Visualizing Uncertainty-to-Action Composition for Human Oversight](https://mlsanity.com/paper/2608.16428/) (2026)
- [Responsible Integration of AI in Cancer Genomics: Barriers, Risks, and Pathways to Trustworthy Clinical Translation](https://mlsanity.com/paper/2608.30912/) (2026)

## Abstract (arXiv)

Explainable Artificial Intelligence (XAI) techniques, such as SHapley Additive exPlanations (SHAP), have become essential tools for interpreting complex ensemble tree-based models, especially in high-stakes domains such as healthcare analytics. However, SHAP values are usually treated as point estimates, which disregards the inherent and ubiquitous uncertainty in predictive models and data. This uncertainty has two primary sources: aleatoric and epistemic. The aleatoric uncertainty, which reflects the irreducible noise in the data. The epistemic uncertainty, which arises from a lack of data. In this work, we propose an approach for decomposing uncertainty in SHAP values into aleatoric, epistemic, and entanglement components. This approach integrates Dempster-Shafer evidence theory and hypothesis sampling via Dirichlet processes over tree ensembles. We validate the method across three real-world use cases with descriptive statistical analyses that provide insight into the nature of epistemic uncertainty embedded in SHAP explanations. The experimentations enable to provide more comprehensive understanding of the reliability and interpretability of SHAP-based attributions. This understanding can guide the development of robust decision-making processes and the refinement of models in high-stakes applications. Through our experiments with multiple datasets, we concluded that features with the highest SHAP values are not necessarily the most stable. This epistemic uncertainty can be reduced through better, more representative data and following appropriate or case-desired model development techniques. Tree-based models, especially bagging, facilitate the effective quantification of epistemic uncertainty.