# Contextual Importance and Utility: aTheoretical Foundation

arXiv: https://arxiv.org/abs/2202.07292 · HTML: https://mlsanity.com/paper/2202.07292/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 15 Feb 2022.

## Builds on (most cited first, 4 of 4)

- [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)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Explainable Artificial Intelligence for Human Decision-Support System in Medical Domain](https://mlsanity.com/paper/2105.02357/) (2021)

## Built on by (most cited first, 5 of 5)

- [Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation](https://mlsanity.com/paper/2606.22901/) (2026)
- [T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems](https://mlsanity.com/paper/2309.16146/) (2023)
- [Do intermediate feature coalitions aid explainability of black-box models?](https://mlsanity.com/paper/2303.11920/) (2023)
- [Context, Utility and Influence of an Explanation](https://mlsanity.com/paper/2303.13552/) (2023)
- [Contextual Importance and Utility in Python: New Functionality and Insights with the py-ciu Package](https://mlsanity.com/paper/2408.09957/) (2024)

## Abstract (arXiv)

This paper provides new theory to support to the eXplainable AI (XAI) method Contextual Importance and Utility (CIU). CIU arithmetic is based on the concepts of Multi-Attribute Utility Theory, which gives CIU a solid theoretical foundation. The novel concept of contextual influence is also defined, which makes it possible to compare CIU directly with so-called additive feature attribution (AFA) methods for model-agnostic outcome explanation. One key takeaway is that the "influence" concept used by AFA methods is inadequate for outcome explanation purposes even for simple models to explain. Experiments with simple models show that explanations using contextual importance (CI) and contextual utility (CU) produce explanations where influence-based methods fail. It is also shown that CI and CU guarantees explanation faithfulness towards the explained model.