A Survey of Explainable AI and Proposal for a Discipline of Explanation Engineering

Clive Gomes, Lalitha Natraj, Shijun Liu, Anushka Datta
5/20/2023
cs.AIcs.HC

No confident code implementation found for this paper.

Abstract

In this survey paper, we deep dive into the field of Explainable Artificial Intelligence (XAI). After introducing the scope of this paper, we start by discussing what an "explanation" really is. We then move on to discuss some of the existing approaches to XAI and build a taxonomy of the most popular methods. Next, we also look at a few applications of these and other XAI techniques in four primary domains: finance, autonomous driving, healthcare and manufacturing. We end by introducing a promising discipline, "Explanation Engineering," which includes a systematic approach for designing explainability into AI systems.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda

86% match2024

Forms of Understanding for XAI-Explanations

84% match2023

Clash of the Explainers: Argumentation for Context-Appropriate Explanations

84% match2023

Understanding XAI Through the Philosopher's Lens: A Historical Perspective

83% match2024

Why Don't You Do Something About It? Outlining Connections between AI Explanations and User Actions

83% match2023

One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

82% match1 repo1.8k2019

Cite this paper

@article{gomes2023survey,
  title  = {A Survey of Explainable AI and Proposal for a Discipline of Explanation Engineering},
  author = {Clive Gomes and Lalitha Natraj and Shijun Liu and Anushka Datta},
  year   = {2023},
  eprint = {2306.01750},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.01750v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.01750.svg)](https://codeofpaper.com/paper/2306.01750)

Discussion