Top Research Papers on Explainable AI

Complex machine learning models perform better. However, we consider these models as black boxes. That’s where Explainable AI (XAI) comes into play. Understanding why a model makes a specific prediction can be as crucial as its accuracy for many applications, researchers, and decision-makers. In many real-world applications, the explainability and transparency of AI systems are indispensable. The research community and industry are giving growing attention to explainability and explainable AI. Compared to traditional machine learning methods, deep neural networks (DNNs) have been very successf...

Explainable Artificial Intelligence (XAI) has emerged as a critical facet in the realm of machine learning and artificial intelligence, responding to the increasing complexity of models, particularly deep neural networks, and the subsequent need for transparent decision making processes. This research paper delves into the essence of XAI, unraveling its significance across diverse domains such as healthcare, finance, and criminal justice. As a countermeasure to the opacity of intricate models, the paper explores various XAI methods and techniques, including LIME and SHAP, weighing their interp...

Artificial Intelligence (AI) and Machine Learning (ML) are gaining increasing attention regarding their potential applications in auditing. One major challenge of their adoption in auditing is the lack of explainability of their results. As AI/ML matures, so do techniques that can enhance the interpretability of AI, a.k.a., Explainable Artificial Intelligence (XAI). This paper introduces XAI techniques to auditing practitioners and researchers. We discuss how different XAI techniques can be used to meet the requirements of audit documentation and audit evidence standards. Furthermore, we demon...

A review on interpretabilities suggested by different research works and categorize them is provided, hoping that insight into interpretability will be born with more considerations for medical practices and initiatives to push forward data-based, mathematically grounded, and technically grounded medical education are encouraged.

This paper presents a comprehensive review of the state-of-the-art on how to build a Trustworthy and eXplainable AI, taking into account that AI is a black box with little insight into its underlying structure.

This paper will review recent approaches to constructing taxonomies of XAI methods and discuss general challenges concerning them as well as their individual advantages and limitations, and propose and discuss three possible solutions.

A taxonomy and categorizing the XAI techniques based on their scope of explanations, methodology behind the algorithms, and explanation level or usage which helps build trustworthy, interpretable, and self-explanatory deep learning models is proposed.

An in-depth and systematic review of recent studies that use XAI models in the scope of the IoT domain and classify the studies according to their methodology and application areas.

Most of state of the art methods applied on time series consist of deep learning methods that are too complex to be interpreted. This lack of interpretability is a major drawback, as several applications in the real world are critical tasks, such as the medical field or the autonomous driving field. The explainability of models applied on time series has not gather much attention compared to the computer vision or the natural language processing fields. In this paper, we present an overview of existing explainable AI (XAI) methods applied on time series and illustrate the type of explanations ...

This Systematic Literature Review (SLR) identifies 138 relevant articles from 2005 to 2022 and highlights empirical examples demonstrating XAI's potential benefits in the financial industry and concisely defines the existing challenges, requirements, and unresolved issues in applying XAI in the financial sector.

A narrative review of XAI and a taxonomy of the XAI literature comprising its precepts and approaches are developed to help alleviate the scepticism and hesitancy toward AI adoption and integration in construction.

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 ...

Floods are natural hazards that lead to devastating financial losses and large displacements of people. Flood susceptibility maps can improve mitigation measures according to the specific conditions of a study area. The design of flood susceptibility maps has been enhanced through use of hybrid machine learning and deep learning models. Although these models have achieved better accuracy than traditional models, they are not widely used by stakeholders due to their black-box nature. In this study, we propose the application of an explainable artificial intelligence (XAI) model that incorporate...

An overview of explainable artificial intelligence (XAI) used in deep learning-based medical image analysis methods and an outlook of future opportunities for XAI inmedical image analysis are presented.

It is argued that the use of post-hoc explanatory methods is useful in many cases, but that these methods have limitations that prohibit reliance as the sole mechanism to guarantee fairness of model outcomes in high-stakes decision-making.

A model is provided that explicitly spells out the main concepts and relations necessary to consider and investigate when evaluating, adjusting, choosing, and developing explainability approaches that aim to satisfy stakeholders' desiderata and can serve researchers from the variety of different disciplines involved in XAI as a common ground.

This paper not only highlights the advancements in XAI and its application in real-world scenarios but also addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts.

Despite widespread adoption and outstanding performance, machine learning models are considered as “black boxes”, since it is very difficult to understand how such models operate in practice. Therefore, in the power systems field, which requires a high level of accountability, it is hard for experts to trust and justify decisions and recommendations made by these models. Meanwhile, in the last couple of years, Explainable Artificial Intelligence (XAI) techniques have been developed to improve the explainability of machine learning models, such that their output can be better understood. In thi...

This survey surveys state-of-the-art programming techniques for XAI and presents the different phases of XAI in a typical machine learning development process, and classify the various XAI approaches and discusses the key differences among the existing XAI techniques.

Landslides are among the most devastating natural hazards, severely impacting human lives and damaging property and infrastructure. Landslide susceptibility maps, which help to identify which regions in a given area are at greater risk of a landslide occurring, are a key tool for effective mitigation. Research in this field has grown immensely, ranging from quantitative to deterministic approaches, with a recent surge in machine learning (ML)-based computational models. The development of ML models, in particular, has undergone a meteoritic rise in the last decade, contributing to the successf...

This research describes how a Shapley additive explanations (SHAP) model can be utilized to interpret the results of a deep learning model that is developed for wildfire susceptibility prediction and infer that developing an explainable model would aid in comprehending the model's decision to map wildfire susceptibility, pinpoint high-contributing components in the prediction model, and consequently control fire hazards effectively.

This study introduces an explainable artificial intelligence (XAI) approach of convolutional neural networks (CNNs) for classification in vibration signals analysis using Gradient class activation mapping (Grad-CAM) to generate the attention of model.

The present work tries to explore the finding that the results obtained from SHAP align with the physical model interpretations, thus suggesting the need to add climatic variables as predictors in the prediction model.

A comprehensive framework of X AI and its possible effects on user behavior has been developed and five dimensions of XAI effects are found: trust, transparency, understandability, usability, and fairness.

This paper addresses XAI concept to enhance trust management by exploring the decision tree model in the area of IDS by using simple decision tree algorithms that can be easily read and even resemble a human approach to decision-making by splitting the choice into many small subchoices for IDS.

It is shown that explanations pave the way for AI systems to reshape users' understanding of the world around them, and that the indiscriminate use of modern explainability methods as an isolated measure to address AI systems' black-box problems can lead to unintended, unforeseen problems.

There are emerging concerns about the Fairness, Accountability, Transparency, and Ethics (FATE) of educational interventions supported by the use of Artificial Intelligence (AI) algorithms. One of the emerging methods for increasing trust in AI systems is to use eXplainable AI (XAI), which promotes the use of methods that produce transparent explanations and reasons for decisions AI systems make. Considering the existing literature on XAI, this paper argues that XAI in education has commonalities with the broader use of AI but also has distinctive needs. Accordingly, we first present a framewo...

A systematic meta-survey for challenges and future research directions in XAI organized in two themes based on machine learning life cycle's phases: design, development, and deployment and contributes to XAI literature by providing a guide for future exploration in the XAI area.

The study indicates that existing vegetation mapping strategies based only on spectral characteristics are insufficient to appropriately classify vegetation covers and proposes a new approach based on spectral and textural features.

This systematic review contributes to the body of knowledge by clustering all the scientific studies via a hierarchical system that classifies theories and notions related to the concept of explainability and the evaluation approaches for XAI methods.

It is proposed that explainable AI systems deliver accompanying evidence or reasons for outcomes and processes; provide explanations that are understandable to individual users; provides explanations that correctly reflect the system’s process for generating the output; and that a system only operates under conditions for which it was designed and when it reaches suf ficient confidence in its output.

This study considers more than 300 papers to comprehensively analyze the main CyberSecurity application fields, like Intrusion Detection Systems, Malware detection, Phishing and Spam detection, BotNets detection, Fraud detection, Zero-Day vulnerabilities, Digital Forensics and Crypto-Jacking, pointing out promising works and new challenges.

We introduce four principles for explainable artificial intelligence (AI) that comprise fundamental properties for explainable AI systems. We propose that explainable AI systems deliver accompanying evidence or reasons for outcomes and processes; provide explanations that are understandable to individual users; provide explanations that correctly reflect the system s process for generating the output; and that a system only operates under conditions for which it was designed and when it reaches sufficient confidence in its output. We have termed these four principles as explanation, meaningful...

Whether explainability can provide added value to CDSS depends on several key questions: technical feasibility, the level of validation in case of explainable algorithms, the characteristics of the context in which the system is implemented, the designated role in the decision-making process, and the key user group(s).

This paper provides a global explainable AI model which is based on Lorenz decomposition, thus extending previous contributions based on variance decompositions, and provides a unifying variable importance criterion that combines predictive accuracy with explainability, using a normalised and easy to interpret metric.

• Emphasizes the need for transparency to build healthcare professionals' trust in AI systems. • Addresses the critical need for explainability due to potential high-impact consequences of AI errors in healthcare. • Categorizes XAI methods into six groups for healthcare research: feature-oriented, global, concept, surrogate, local pixel-based, and human-centric. • Analyzes the significance of XAI in overcoming healthcare-specific challenges. • Provides an exhaustive review of XAI applications and relevant experimental results in healthcare contexts. Explainable Artificial Intelligence (XAI) en...

This position paper brings together seven researchers working in the field with different roles and perspectives to explore in depth the concept of explainable AI, or XAI, offering a functional definition and conceptual framework or model that can be used when considering XAI.

A historical perspective of explainability in AI is presented and criteria for explanations are proposed that are believed to play a crucial role in the development of human‐understandable explainable systems.

This review aims to bridge the gap by discovering the critical perspectives of the rapidly growing body of research associated with XAI by analyzing and reviewing various XAI methods, which are grouped into (i) pre-modeling explainability, (ii) interpretable model, and (iii) post-modelling explainability.

A brief analytical review of the current state‐of‐the‐art in relation to the explainability of artificial intelligence in the context of recent advances in machine learning and deep learning is provided.