article · Information Fusion
This comprehensive review examines Explainable Artificial Intelligence (XAI), addressing the challenge of understanding and trusting complex AI models due to their black-box nature. It provides an overview of current research and trends, explaining XAI background, common definitions, and recently proposed techniques for supervised machine learning. The study categorises XAI methods into data, model, post-hoc, and assessment explainability. It also introduces available evaluation metrics, open-source packages, and datasets, alongside outlining XAI concerns related to legal demands, user viewpoints, and application orientation. The review, based on 410 articles, advocates for tailoring explanation content to specific user types.
As AI becomes more prevalent, its black-box nature can hinder trust and adoption. This review is vital for understanding how to make AI decisions transparent and reliable. It provides a foundational resource for researchers to develop more trustworthy AI systems, which is crucial for responsible AI deployment across various sectors.
This research provides a comprehensive overview of XAI methods, tools, and challenges, which is foundational for developing more transparent and trustworthy AI systems. While not a direct product, it informs the design and implementation of AI applications where understanding and trust are paramount, such as in healthcare diagnostics or financial decision-making. This is early-stage research, providing a knowledge base for future applied development.
AI-generated from the published abstract. Always read the original work before citing.
Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated applications, but the outcomes of many AI models are challenging to comprehend and trust due to their black-box nature. Usually, it is essential to understand the reasoning behind an AI model’s decision-making. Thus, the need for eXplainable AI (XAI) methods for improving trust in AI models has arisen. XAI has become a popular research subject within the AI field in recent years. Existing survey papers have tackled the concepts of XAI, its general terms, and post-hoc explainability methods but there have not been any reviews that have looked at the assessment methods, available tools, XAI datasets, and other related aspects. Therefore, in this comprehensive study, we provide readers with an overview of the current research and trends in this rapidly emerging area with a case study example. The study starts by explaining the background of XAI, common definitions, and summarizing recently proposed techniques in XAI for supervised machine learning. The review divides XAI techniques into four axes using a hierarchical categorization system: (i) data explainability, (ii) model explainability, (iii) post-hoc explainability, and (iv) assessment of explanations. We also introduce available evaluation metrics as well as open-source packages and datasets with future research directions. Then, the significance of explainability in terms of legal demands, user viewpoints, and application orientation is outlined, termed as XAI concerns. This paper advocates for tailoring explanation content to specific user types. An examination of XAI techniques and evaluation was conducted by looking at 410 critical articles, published between January 2016 and October 2022, in reputed journals and using a wide range of research databases as a source of information. The article is aimed at XAI researchers who are interested in making their AI models more trustworthy, as well as towards researchers from other disciplines who are looking for effective XAI methods to complete tasks with confidence while communicating meaning from data.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.inffus.2023.101805
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
