24 papers · ranked by Valyu relevance
Kaivalya Rawal, Eoin Delaney, Zihao Fu, Sandra Wächter + 1 more
Explainable artificial intelligence (XAI) is concerned with producing explanations indicating the inner workings of models. For a Rashomon set of similarly performing models, explanations provide a way of disambiguating the behavior of individual models, helping select models for deployment. However explanations…
Michael Merry, Pat Riddle, Jim Warren
We propose a globally applicable criterion for inherent explainability. The criterion uses graph theory for representing and decomposing models for structure-local explanation, and recomposing them into global explanations. We form the structure-local explanations as annotations, a verifiable hypothesis-evidence…
Matteo Rizzo, Alberto Veneri, Matteo Marcuzzo, Alessandro Zangari + 4 more
Explainable Artificial Intelligence, or XAI, is a vibrant research topic in the artificial intelligence community. It is raising growing interest across methods and domains, especially those involving high-stakes decision-making, such as the biomedical sector. Much has been written about the subject, yet XAI still…
Anna Rodum Bjøru, Jacob Lysnæs-Larsen, Oskar Jørgensen, Inga Strümke + 1 more
This work presents a conceptual framework for causal concept-based post-hoc Explainable Artificial Intelligence (XAI), based on the requirements that explanations for non-interpretable models should be understandable as well as faithful to the model being explained. Local and global explanations are generated by…
Fang Tang, Renqi Zhu, Feng Yao, Junzhi Wang + 2 more
Introduction As person-job recommendation systems (PJRS) increasingly mediate hiring decisions, concerns over their “black box” opacity have sparked demand for explainable AI (XAI) solutions. Methods This systematic review examines 85 studies on explainable PJRS methods published between 2019 and August 2025, selected…
Yongze Song, Filip Biljecki, Gustau Camps-Valls, Peter M. Atkinson
Geospatial artificial intelligence (GeoAI) is reshaping our understanding of Earth and urban systems by integrating advanced artificial intelligence techniques with diverse geospatial data and methodologies. This backstory highlights recent GeoAI advances and applications as presented in the 11 articles in the iScience…
Logan Brase, Declan R. Creamer, Yuliya Shapovalova, Mark P. Ashe + 2 more
The regulation of mRNA decay and translation is crucial for cellular function and development; however, the complex interplay of RNA-binding proteins (RBPs) regulating these processes remains incompletely understood. Recent advances in genomic foundation models present new opportunities for decoding the regulatory…
Authors not listed
Predicting drug-induced toxicity remains a central challenge in computational toxicology, particularly for organ-specific adverse effects that arise from diverse structural, biochemical, and mechanistic origins. Existing deep learning models excel at pattern recognition but often lack mechanistic interpretability…
Yicheng Gao, Weixu Wang, Yuheng Zhao, Kejing Dong + 7 more
Decoding cellular systems requires integrating diverse omics data, yet most models are trained from scratch on a single modality, restricting generalization. Here we present CellHermes, a biological language model that leverages pretrained large language models (LLMs) to integrate multimodal forms of omics data, such…
Mohamed Ebraheem, Jamie Toghranegar, Yael Bensoussan, John Michael Templeton + 1 more
Background Driven by recent advances in artificial intelligence (AI), particularly in medicine, audio-based voice and speech biomarkers are increasingly investigated for various medical applications as a complementary or even alternative modality to traditional medical devices. The adoption of deep learning techniques…
Christian Oliva, Luis F. Lago-Fernández
The rapid adoption of deep learning models in high-risk domains has intensified the need for trustworthy Explainable Artificial Intelligence (XAI). However, objectively evaluating explanation fidelity and aligning XAI metrics with human-centered understanding remain critical open challenges. In this work, we propose a…
Boris Babic, I. Glenn Cohen, Julian Savulescu
As artificial intelligence and machine learning (AI/ML) systems become increasingly pervasive in society, their opacity-i.e., the difficulty, and sometimes impossibility, of understanding why they make the decisions they make-has become a serious problem. This is especially true in sensitive decision-making contexts…
Kaiyun Guo, Jiarui Ding
Cell type annotation is a fundamental task in single-cell genomics. Although various methods have been developed for automatic cell type annotation, they often function as black-box models, making predictions without explaining their reasoning and lacking proper uncertainty estimation for their predictions.…
Authors not listed
Olfaction arises from the interaction of odorants with olfactory receptors, a process shaped by molecular geometry, electron distribution, and conformational preference. We present ConfDENSE, a Set2Set enhanced PointNet model that learns directly from Hirshfeld promolecule electron-density point clouds, preserving full…
Jules Soria, Zakaria Chihani, Julien Girard-Satabin, Alban Grastien + 2 more
Case-based reasoning networks are machine-learning models that make predictions based on similarity between the input and prototypical parts of training samples, called prototypes. Such models are able to explain each decision by pointing to the prototypes that contributed the most to the final outcome. As the…
Lenka Tětková, Erik Schou Dreier, Robin Malm, Lars Kai Hansen + 1 more
Much machine learning research progress is based on developing models and evaluating them on a benchmark dataset (e.g., ImageNet for images). However, applying such benchmark-successful methods to real-world data often does not work as expected. This is particularly the case for biological data where we expect…
Mrinal Mahindran, Qingyuan (Chingyuen) Liu, Vishak Madhwaraj Kadambalithaya, Olga V Kalinina
Predicting drug-target interactions (DTI) with graph neural networks (GNNs) is hindered by their lack of interpretability. To address this, we benchmark four explainable artificial intelligence (XAI) attribution methods on GNN models trained for kinase and GPCR targets. We assess the methods’ consistency through…
Michal Moshkovitz, Suraj Srinivas, Lesia Semenova, Nave Frost + 6 more
Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions to sparse autoencoders -- explanations rarely influence real-world workflows. In practice, they are often generated and discarded without guiding meaningful action. This gap reflects foundational shortcomings: research has not yet…
Arno Leue, Akhila Bairy, Maike Schwammberger
Autonomous and software-intensive systems have been growing in occurrence, complexity, and assumed responsibility. Due to the high complexity of these systems, properties like transparency and explainability must be a focus of investigation. To date, no universally applicable definition and guide for the development of…
Muwei Li
Naturalistic paradigms offer a powerful window into human cognition, but it remains difficult to link rich, continuous movie content to distributed brain activity in an interpretable way. In this study, I use a multimodal large language model (Gemini) as an automated “semantic annotator” to bridge naturalistic movie…
Authors not listed
Background: Batch reactor process optimization has traditionally relied on Analysis of Variance (ANOVA) for factor effect quantification. However, Structural Equation Modeling (SEM) and machine learning (ML) offer complementary mechanistic and predictive capabilities that remain underexplored in chemical engineering…
David Martínez-Enguita, Thomas Hillerton, Julia Åkesson, Maria Lerm + 1 more
Genome-scale DNA methylation (DNAm) profiles capture organismal physiology, but most predictive models lack transparency and multi-level applicability. Here we develop an explainable framework that quantifies respiratory, cardiovascular, and metabolic status as bounded health scores (0–1) derived from sex-specific…
Authors not listed
Graph Neural Networks (GNNs) are powerful tools for molecular property prediction, but they are not magic. When applied to molecules unlike their training data, they produce unreliable predictions that are difficult to detect. The Applicability Domain (AD) concept addresses this by defining regions of chemical space…
Authors not listed
Background: Pharmaceutical batch scheduling in multi-reactor configurations presents complex optimization challenges under operational uncertainty, yet limited research addresses how parallel processing capacity affects heuristic performance and predictive modeling. Objectives: This study investigated scheduling…