# Altruist: Argumentative Explanations through Local Interpretations of Predictive Models

arXiv: https://arxiv.org/abs/2010.07650 · HTML: https://mlsanity.com/paper/2010.07650/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2020.

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

- [LioNets: A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information](https://mlsanity.com/paper/2104.06057/) (2021)
- [VisioRed: A Visualisation Tool for Interpretable Predictive Maintenance](https://mlsanity.com/paper/2103.17003/) (2021)
- [Developing Guidelines for Functionally-Grounded Evaluation of Explainable Artificial Intelligence using Tabular Data](https://mlsanity.com/paper/2410.12803/) (2024)
- [Truthful Meta-Explanations for Local Interpretability of Machine Learning Models](https://mlsanity.com/paper/2212.03513/) (2022)
- [Argumentation and Machine Learning](https://mlsanity.com/paper/2410.23724/) (2024)

## Abstract (arXiv)

Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques are often not comprehensible to the end user. Lack of evaluation and selection criteria also makes it difficult for the end user to choose the most suitable technique. In this study, we combine logic-based argumentation with Interpretable Machine Learning, introducing a preliminary meta-explanation methodology that identifies the truthful parts of feature importance oriented interpretations. This approach, in addition to being used as a meta-explanation technique, can be used as an evaluation or selection tool for multiple feature importance techniques. Experimentation strongly indicates that an ensemble of multiple interpretation techniques yields considerably more truthful explanations.