Top Research Papers on Explainable AI

A systematic cross-domain review of XAI techniques applied to quantitative prediction tasks, with a focus on their methodological relevance and potential adaptation to biomedical imaging and sensing, and provides guidance for future research aimed at safe and interpretable AI deployment in biomedical imaging and sensing.

A novel rule-based XAI strategy (including pre-processing, knowledge-extraction and functional validation) for finding biologically relevant sequential patterns from longitudinal human gene expression data (GED) and proves the goodness of this strategy for the mining of biologically relevant gene-gene temporal relations.

This study explores the application of Explainable AI (XAI) to address the inherent limitations of traditional "black-box" AI models, emphasizing transparency and interpretability in high-stakes domains such as natural hazard management.

It is shown that XAI method, applied at point-scale, could be used for cross-scale aggregation of hydrologic responses, a fundamental question in scaling problems, using hydrologic connectivity as a demonstration.

Amblyopia is a neurodevelopmental disorder affecting children's visual acuity, requiring early diagnosis for effective treatment. Traditional diagnostic methods rely on subjective evaluations of eye tracking recordings from high fidelity eye tracking instruments performed by specialized pediatric ophthalmologists, often unavailable in rural, low resource clinics. As such, there is an urgent need to develop a scalable, low cost, high accuracy approach to automatically analyze eye tracking recordings. Large Language Models (LLM) show promise in accurate detection of amblyopia; our prior work has...

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 article concludes that XAI can contribute to the identification of biases in algorithmic models, then it is suggested that the ability to “explain” should be a requirement for adopting AI systems in sensitive areas such as court decisions.

This research work focuses on the prediction of the surface roughness of additive-manufactured polylactic acid (PLA) specimens using eight different supervised machine learning regression-based algorithms, and demonstrates that the XGBoost algorithm provides the most accurate predictions for surface Roughness compared with other algorithms.

This work trains linear regression and convolutional neural network models to make one-day predictions of sea-ice velocity in the Arctic from inputs of present-day wind velocity and previous-day ice velocity and concentration, and shows that wind speed over land is highly relevant for predicting ice motion offshore.

The results indicated that incorporating XAI and textual summaries significantly improved expert explainability and increased confidence in the model’s ability to support treatment decisions for ADPKD patients.

It is suggested that XAI considerably improves trust and understanding among project managers, which further boosts the quality of decision-making processes and empirically prove the significance of XAI as a method of creating grounds of trust and comprehension within the project management environment.

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.

A new unified yet simple taxonomy for the categorization of XAI methods and present the explainability methods currently being applied in finance applications is provided.

It was found that behavioral and academic performance data were the most commonly used features, with the main prediction goals focused on course failure risk or grades, and SHapley Additive exPlanations were the most frequently utilized XAI technique.

Comparison of various predictive models (logistic regression, logistic regression with weight of evidence transformations and modern artificial intelligence algorithms) are presented and it is shown that advanced tree based models give best results in prediction of client default.

This survey presents a comprehensive review of state-of-the-art ML techniques for malware analysis, with a specific focus on explainability methods, and examines existing XAI frameworks, their application in malware classification and detection, and the challenges associated with making malware detection models more interpretable.

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.

An interpretable machine learning methodology with cyber security for integrating Explainable AI methods designed to improve an analyst's or team's ability to both operate a threat detection model, and enhance a model, in terms of performance, usability and interpretability is introduced.

A deep learning model with a multi-layer perceptron architecture is used to predict MR and DS based on aggregate gradation parameters derived from Bailey's Method, including coarse aggregate ratio (CA), fine aggregate coarse ratio (FAc), and other mix design variables.

Drug discovery is a complex, lengthy, and costly process with a high failure rate, especially during clinical trials. The integration of Artificial Intelligence (AI) has revolutionized various stages of drug discovery by enabling faster and more accurate analysis of biological and chemical data. However, most AI models in this field operate as “black boxes,” where their decision-making processes are opaque and difficult to interpret. This lack of transparency poses significant challenges in terms of trust, validation, and adoption of AI-generated predictions in both clinical and regulatory set...