# Can I trust you more? Model-Agnostic Hierarchical Explanations

arXiv: https://arxiv.org/abs/1812.04801 · HTML: https://mlsanity.com/paper/1812.04801/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2018.

## Built on by (most cited first, 10 of 10)

- [Explanations of Black-Box Models based on Directional Feature Interactions](https://mlsanity.com/paper/2304.07670/) (2023)
- [Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks](https://mlsanity.com/paper/2104.04488/) (2021)
- [Feature Interactions Reveal Linguistic Structure in Language Models](https://mlsanity.com/paper/2306.12181/) (2023)
- [Interpretable Artificial Intelligence through the Lens of Feature Interaction](https://mlsanity.com/paper/2103.03103/) (2021)
- [iLOCO: Distribution-Free Inference for Feature Interactions](https://mlsanity.com/paper/2502.06661/) (2025)
- [When Stability meets Sufficiency: Informative Explanations that do not Overwhelm](https://mlsanity.com/paper/2109.06181/) (2021)
- [Advancing Interpretability in Text Classification through Prototype Learning](https://mlsanity.com/paper/2410.17546/) (2024)
- [Interpreting and improving deep-learning models with reality checks](https://mlsanity.com/paper/2108.06847/) (2021)
- [Why is "Problems" Predictive of Positive Sentiment? A Case Study of Explaining Unintuitive Features in Sentiment Classification](https://mlsanity.com/paper/2406.03594/) (2024)
- [Algebraic Learning: Towards Interpretable Information Modeling](https://mlsanity.com/paper/2203.06690/) (2022)

## Abstract (arXiv)

Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models. We propose Mah'e, a novel approach to provide Model-agnostic hierarchical 'explanations of how powerful machine learning models, such as deep neural networks, capture these interactions as either dependent on or free of the context of data instances. Specifically, Mah'e provides context-dependent explanations by a novel local interpretation algorithm that effectively captures any-order interactions, and obtains context-free explanations through generalizing context-dependent interactions to explain global behaviors. Experimental results show that Mah'e obtains improved local interaction interpretations over state-of-the-art methods and successfully explains interactions that are context-free.