# CHILLI: A data context-aware perturbation method for XAI

arXiv: https://arxiv.org/abs/2407.07521 · HTML: https://mlsanity.com/paper/2407.07521/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 15 of 15)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- ["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)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations](https://mlsanity.com/paper/1907.09294/) (2019)
- [Discrimination in Online Ad Delivery](https://mlsanity.com/paper/1301.6822/) (2013)
- [Explaining the Explainer: A First Theoretical Analysis of LIME](https://mlsanity.com/paper/2001.03447/) (2020)
- [General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models](https://mlsanity.com/paper/2007.04131/) (2020)
- [Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approach](https://mlsanity.com/paper/2006.04628/) (2020)
- [Designing Inherently Interpretable Machine Learning Models](https://mlsanity.com/paper/2111.01743/) (2021)
- [bLIMEy: Surrogate Prediction Explanations Beyond LIME](https://mlsanity.com/paper/1910.13016/) (2019)
- [Predicting Hospital Re-admissions from Nursing Care Data of Hospitalized Patients](https://mlsanity.com/paper/1702.04036/) (2017)
- [An Unsupervised Multivariate Time Series Kernel Approach for Identifying Patients with Surgical Site Infection from Blood Samples](https://mlsanity.com/paper/1803.07879/) (2018)
- [Towards Fully Interpretable Deep Neural Networks: Are We There Yet?](https://mlsanity.com/paper/2106.13164/) (2021)

## Built on by (most cited first, 1 of 1)

- [XMACNet: An Explainable Lightweight Attention based CNN with Multi Modal Fusion for Chili Disease Classification](https://mlsanity.com/paper/2603.06750/) (2026)

## Abstract (arXiv)

The trustworthiness of Machine Learning (ML) models can be difficult to assess, but is critical in high-risk or ethically sensitive applications. Many models are treated as a `black-box' where the reasoning or criteria for a final decision is opaque to the user. To address this, some existing Explainable AI (XAI) approaches approximate model behaviour using perturbed data. However, such methods have been criticised for ignoring feature dependencies, with explanations being based on potentially unrealistic data. We propose a novel framework, CHILLI, for incorporating data context into XAI by generating contextually aware perturbations, which are faithful to the training data of the base model being explained. This is shown to improve both the soundness and accuracy of the explanations.