# Unified Explanations in Machine Learning Models: A Perturbation Approach

arXiv: https://arxiv.org/abs/2405.20200 · HTML: https://mlsanity.com/paper/2405.20200/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 31 references that are in the map.
- First posted on arXiv 30 May 2024.

## Builds on (most cited first, 8 of 8)

- [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)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Adversarial Attacks and Defenses in Images, Graphs and Text: A Review](https://mlsanity.com/paper/1909.08072/) (2019)
- [Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers](https://mlsanity.com/paper/1604.00825/) (2016)
- [Investigating Bias in Deep Face Analysis: The KANFace Dataset and Empirical Study](https://mlsanity.com/paper/2005.07302/) (2020)
- [Domain-independent generation and classification of behavior traces](https://mlsanity.com/paper/2011.02918/) (2020)

## Built on by (most cited first, 2 of 2)

- [RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems](https://mlsanity.com/paper/2509.10746/) (2025)
- [Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks](https://mlsanity.com/paper/2510.06307/) (2025)

## Abstract (arXiv)

A high-velocity paradigm shift towards Explainable Artificial Intelligence (XAI) has emerged in recent years. Highly complex Machine Learning (ML) models have flourished in many tasks of intelligence, and the questions have started to shift away from traditional metrics of validity towards something deeper: What is this model telling me about my data, and how is it arriving at these conclusions? Inconsistencies between XAI and modeling techniques can have the undesirable effect of casting doubt upon the efficacy of these explainability approaches. To address these problems, we propose a systematic, perturbation-based analysis against a popular, model-agnostic method in XAI, SHapley Additive exPlanations (Shap). We devise algorithms to generate relative feature importance in settings of dynamic inference amongst a suite of popular machine learning and deep learning methods, and metrics that allow us to quantify how well explanations generated under the static case hold. We propose a taxonomy for feature importance methodology, measure alignment, and observe quantifiable similarity amongst explanation models across several datasets.