This paper introduces an entropy-centric Explainable AI (XAI) method for semantic segmentation in remote sensing imagery. It also proposes a novel XAI evaluation methodology, demonstrating superior performance compared to existing methods in identifying relevant regions for model decisions.

This paper evaluates the suitability and limitations of Explainable AI (XAI) methods for regression problems prevalent in geoscientific applications. It reviews various XAI techniques, applies a selection to a machine learning emulator of the Lorenz-63 system, and surveys their use across Earth system sciences to provide practical recommendations for effective XAI.

This paper explores the significant limitations in evaluating Explainable AI (XAI) methods, particularly focusing on the scarcity of robust human-grounded evaluations and the challenges posed by evolving data streams with concept drift. It highlights the need for more systematic and interdisciplinary approaches to assess the effectiveness and trustworthiness of AI explanations.

This paper introduces a scalable web-based visual analytics system to overcome challenges in translating AI and radiomics into clinical practice for brain tumor research. It integrates cohort management, radiomic feature extraction, and guarded machine learning inference within a single, transparent interface.

This paper introduces PREF-XAI, a novel approach for generating personalized, rule-based explanations of black-box machine learning models. It reframes explanation as a preference-driven decision problem, learning individual user preferences through robust ordinal regression to tailor explanations.

This study introduces a dual-modal AI framework combining CT radiology and H&E microscopy with clinical data for improved lung cancer diagnosis and subtype classification. The system demonstrates high accuracy and interpretability, offering a more robust and transparent approach to overcome the limitations of single-modality diagnostic methods.

Current methods using LLMs to translate technical XAI outputs into natural language often lack guarantees of accuracy and completeness. This paper introduces a Two-Stage LLM Meta-Verification Framework that employs an Explainer LLM for generating explanations and a Verifier LLM to assess and refine them iteratively, significantly enhancing the trustworthiness and accessibility of XAI.

This review introduces a framework that combines deep learning with committor analysis and explainable AI (XAI) to systematically identify reaction coordinates in complex molecular systems. The approach enables the quantitative assessment of individual input variable contributions, enhancing the interpretability of molecular transition pathways.

This study introduces a novel framework for Mathematical Entity Relation Extraction (MERE) using transformer-based models, achieving 99.39% accuracy with BERT. It integrates Explainable AI (XAI) via SHAP to enhance transparency, providing insights into feature importance and model behavior for improved mathematical text understanding.

This paper introduces PONTE, a human-in-the-loop framework for generating personalized and trustworthy natural language explanations from AI systems. It employs a closed-loop validation and adaptation process to ensure faithfulness, completeness, and stylistic alignment with user preferences, mitigating common issues associated with large language models in Explainable AI.