Top Research Papers on Explainable AI

A new frontier is opening for researchers in explainability and explainable AI, where a new frontier is opening for researchers to interpret the behavior and predictions of neural networks.

This research presents a meta-modelling architecture that automates the very labor-intensive and therefore time-heavy and therefore expensive and expensive process of manually cataloging and cataloging artificial intelligence applications.

The field of explainable artificial intelligence (XAI) advances techniques, processes, and strategies that provide explanations for the predictions, recommendations, and decisions of opaque and complex machine learning systems. Increasingly academic libraries are providing library users with systems, services, and collections created and delivered by machine learning. Academic libraries should adopt XAI as a tool set to verify and validate these resources, and advocate for public policy regarding XAI that serves libraries, the academy, and the public interest.

This research paper delves into the essence of XAI, unraveling its significance across diverse domains such as healthcare, finance, and criminal justice and scrutinizes the delicate balance between interpretability and performance, shedding light on instances where the pursuit of accuracy may compromise explain-ability.

An overview of XAI and its techniques for creating interpretable models, specifically focusing on Local Interpretable Model-Agnostic Explanations and SHapley Additive exPlanations are presented.

This paper investigates XAI for algorithmic trustworthiness and transparency using some example use cases and by using SHAP (SHapley Additive exPlanations) library and visualizing the effect of features individually and cumulatively in the prediction process.

The study finds that XAI methods are particularly prevalent in claims management, underwriting and actuarial pricing practices, and proposes an adapted definition of XAI informed by the systematic review ofXAI literature in insurance.

This session will go over why the AI needs to be explainable, what does that mean, the state of the art of explainable AI as well as various approaches to build it.

It is postulate that the future of human-centric XAI is neither in explaining black-boxes nor in reverting to traditional, interpretable models, but in neural networks that are intrinsically interpretable.

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.

In a series of ongoing evaluations, the developer teams are assessing how well their XAM systems’ explanations improve user understanding, user trust, and user task performance.

The use of Artificial Intelligence in the context of decision analytics and service science has received significant attention in academia and practice alike, but much of the current efforts have focused on advancing underlying algorithms and not on decreasing the complexity of AI systems.

The key role of XAI in shaping future trends in marketing research and its implications for businesses operating in a dynamic market environment are highlighted, with the aim of driving marketing practices in a data-dominated era.

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.

A systematic review of xAI literature on the topic identifies four thematic debates central to how xAI addresses the black-box problem and synthesizes the findings into a future research agenda to further the xAI body of knowledge.

The DARPA's Explainable Artificial Intelligence (XAI) program endeavors to create AI systems whose learned models and decisions can be understood and appropriately trusted by end users. This talk will summarize the XAI program and present highlights from these Phase 1 evaluations.

The remarkable advancements in Deep Learning (DL) algorithms have fueled enthusiasm for using Artificial Intelligence (AI) technologies in almost every domain; however, the opaqueness of these algorithms put a question mark on their applications in safety-critical systems. In this regard, the `explainability' dimension is not only essential to both explain the inner workings of black-box algorithms, but it also adds accountability and transparency dimensions that are of prime importance for regulators, consumers, and service providers. eXplainable Artificial Intelligence (XAI) is the set of te...

It is argued that the supposed trade-off between explainability and performance is best approached in a nuanced way that incorporates resource availability, domain characteristics, and considerations of risk.

It is argued that central to the XAI endeavor is the requirement that automated explanations provided by an AI system should make sense to human users.

The significance of this article lies in introducing the “social explanation” concept in XAI, which has been underexplored in the previous literature, and demonstrating how social explanations can be effectively employed to tackle misinformation and promote collaboration across diverse fields by drawing upon interdisciplinary techniques.

This research targets to delve into various methodologies geared toward making those fashions greater interpretable, understandable, and in the long run extra straightforward, to bridge the space among the inherent complexity of superior device studying models and the need for obvious decision-making methods.

This review focuses on the requirement that XAIs must be able to explain in detail the decisions made by the AI to the experts in the field.

A conceptual review explores the significance of XAI in promoting trust and transparency in AI systems, analyzes existing literature on XAI, identifies patterns and gaps, and presents a coherent conceptual framework.

This paper analyze legislative and policy developments in the United States and the European Union, such as the Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence, the AI Act, the AI Liability Directive, and the General Data Protection Regulation from a right to explanation perspective from a right to explanation perspective to argue that these AI regulations and current market conditions threaten effective AI governance and safety.

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.

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.

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.

Utilization of model-agnostic explainable artificial intelligence frameworks in oncology: a narrative explores the role of models in medicine and the role that models play in medicine's therapeutic decisions.

This narrative review will have a look at some central concepts in XAI, describe several challenges around XAI in healthcare, and discuss whether it can really help healthcare to advance by increasing understanding and trust.

The argument presented is that xAI is crucial in contexts as it empowers judges to make informed decisions based on algorithmic outcomes, and the lack of transparency, in decision-making processes can impede judge's ability to do effectively.

This paper presents an overview of existing explainable AI (XAI) methods applied on time series and illustrates the type of explanations they produce and provides a reflection on the impact of these explanation methods to provide confidence and trust in the AI systems.

This study aims to demystify the decision-making processes of the prediction model using XAI, essential for the ethical deployment of AI, fostering trust and transparency in these systems.

To increase people’s trust in adopting AI models, it is important a complete interpretability of the behaviour of AI-models is shown.

This work focuses on three main attributes that describe automatically-generated explanations from existing XAI algorithms (format, complexity, and specificity), and captures differences across contexts (online targeted advertising vs. loan applications) as well as heterogeneity in users’ cognitive styles.

This abstract explores the necessity of using Explainable AI (XAI) to threat intelligence advancement, clarifying its importance, approaches, difficulties, and potential applications.

This manuscript embarks on a comprehensive exploration of the strides made in XAI, meticulously dissecting its significance, fundamental methodologies, practical applications, hurdles, ethical dimensions, and trajectories for future advancement.

AUTOLYCUS, a novel retraining (learning) based model extraction attack framework against interpretable models under black-box settings, is proposed and shown to be highly effective, requiring significantly fewer queries compared to state-of-the-art attacks, while maintaining comparable accuracy and similarity.

This work uses keyword search using the SemanticScholar API and manual curation to collect a well-formatted and reasonably comprehensive set of 5199 XAI papers, to clarify and visualize trends about the size and scope of the literature, citation trends, cross-field trends, and collaboration trends.

HistoMapr-Breast is described, an initial xAI enabled software application for breast core biopsies that automatically previews breast core WSIs and recognizes the regions of interest to rapidly present the key diagnostic areas in an interactive and explainable manner.

From this article, one can understand the analysis of Alzheimer's by using XAI with the corresponding feature explanation, so that the result is much more trustable and reliable.

This work distill XAI methodologies into data mining operations on training and testing data across modalities, such as images, text, and tabular data, as well as on training logs, checkpoints, models and other DNN behavior descriptors.

Based on the findings, XAI techniques can bring new insights and opportunities for addressing critical maintenance issues, resulting in more informed decisions, and the results analysis suggests a viable path for future studies.

A systematic review of the works organized by body systems is given, and the application of XAI approaches to age prediction tasks are discussed, in particular, in the age prediction domain.

A common approach to build explainable models that may fulfill current challenges of XAI is conceptualized and brought some open research agenda in these findings and future directions.

The state-of-the-art XAI techniques are introduced to accounting researchers and practitioners using terms familiar to them and a framework on how different X AI techniques can be used to meet requirements of existing auditing standards is provided.

The concept of Federated Learning of eXplainable AI (XAI) models, in short FED-XAI, purposely designed to address these two requirements simultaneously of preserving the data privacy and ensuring a certain level of explainability of the system.

This novel perspective is intended to augment the perspective of other authors by focusing less on the EMs themselves but on what explainability approaches intend to achieve (i.e., provide good explanatory information, facilitate understanding, satisfy societal desiderata).

A predictive model for heart disease with 96.07% accuracy is developed, integrating factors like peak exercise ST segment slope, maximum heart rate, and exercise-induced angina, and enables interpretable predictions, facilitating early detection and informed management.

The current report aims to propose suitable metrics for evaluating XAI systems from the perspective of the cognitive states and processes of stakeholders, and elaborate on 7 dimensions, i.e., goodness, satisfaction, user understanding, curiosity&engagement, trust&reliance, controllability&interactivity, and learning curve&productivity.

The theoretical foundations of Explainable Artificial Intelligence (XAI) are provided, clarifying diffuse definitions and identifying research objectives, challenges, and future research lines related to turning opaque machine learning outputs into more transparent decisions.