Explainable Artificial Intelligence

Also known as XAI

Overview

Explainable artificial intelligence studies how to show why models make particular predictions or take actions, so people can assess errors, bias, uncertainty, and appropriate use. Common approaches include post-hoc feature attribution such as SHAP and LIME, saliency maps for images, counterfactual examples, and models designed around interpretable rules or concepts; newer systems also turn evidence and execution traces into interactive or natural-language explanations. Researchers test whether explanations reflect model behavior and remain stable, but increasingly also measure whether people can understand them and make better decisions in settings such as healthcare, finance, cybersecurity, and autonomous systems. A central tension is that explanations that are faithful to complex models may be difficult to use, while fluent or persuasive explanations can encourage misplaced trust without improving understanding or decisions.

Latest papers

CardsList

343 papers18 papers in the last four weeks, down 38% on the four weeks before. 0.1% of all new papers.

  1. When Are Concept Bottleneck Model Explanations Faithful and Compact?

    Oct 5, 2026Stefano Teso, Emanuele Marconato, Steve Azzolin +1Explainable Artificial IntelligenceConcept Bottleneck Models

  2. GFGE: Unifying Explainable AI Methods through an Interpretation Framework

    Oct 4, 2026Jinfeng ZhongExplainable Artificial Intelligence

  3. Specific Algorithmic Interpretability of Neural Networks: A Case Study on Textures

    Oct 3, 2026Yanglin Zhang, Anneke von Seeger, Gilad Lerman +1automated interpretabilityWavelet Scattering Transforms

  4. CyTReX: Explainable AI-Based Cybersecurity Threat Reasoning Framework for DER Networks

    Oct 3, 2026Damilola Popoola, Souradeep Bhattacharya, Manimaran GovindarasuCybersecurityExplainable Artificial Intelligence

  5. HXAI: Hierarchical Privacy-Preserving Explainable AI in Distributed Energy Systems

    Oct 1, 2026Poushali Sengupta, Sabita Maharjan, Frank Eliassen +1Explainable Artificial IntelligencePower Systems

  6. MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations

    Oct 1, 2026Yuyang Cheng, Raghav Kaushik Ravi, Srivarshinee Sridhar +3Explainable Artificial IntelligenceFaithfulness of Language Model Explanations

  7. Do Better Scores Mean Better Physics? Physics-Grounded Explanations for Sim2Real Neural Operators

    Sep 30, 2026Somyajit Chakraborty, Xizhong ChenNeural Surrogate ModelingExplainable Artificial Intelligence

  8. Caption-Mediated Perceived-Safety Estimation for Pedestrian Routing

    Sep 29, 2026Simon Parkinson, Paloma Liu, Wei Zheng +1VLM EvaluationExplainable Artificial Intelligence

  9. HyDI: A hybrid Deep Learning-Inductive Logic Programming ensemble for multi-label classification

    Sep 29, 2026Simon Flügel, Till Mossakowskihierarchical multi-label classificationMulti-Label Classification

  10. A decision-support system applied to Law: Reasoning and explainability of the decision

    Sep 28, 2026Jeremy Bouche-Pillon, Pascale Zarat{é}, Yannick Chevalier +1Logical ReasoningExplainable Artificial Intelligence

  11. Explainable and Generalisable LLM-based Cognitive Decline Detection with Spontaneous Speech

    Sep 28, 2026Ziyun Cui, Wen Wu, Chuan Shi +10Explainable Artificial IntelligenceSpeech-Based Dementia Detection

  12. Mask-Induced Displacement in Audio XAI via Logit Trajectory Decomposition

    Sep 27, 2026Nico García-Peguinho, David Kelly, Fabrizio Smeraldi +1Explainable Artificial IntelligencePerturbation-Based Feature Attribution

  13. Explainable Deep Learning of Resting-State Functional Connectomes Reveals Network Biomarkers of Adolescent Intelligence

    Sep 27, 2026Md. Tanvir Rahman, Nabil Anan Orka, Asaduzzaman Khan +1Explainable Artificial IntelligenceFunctional Connectivity

  14. Evaluating Single and Multi-Omics Based Explainable Artificial Intelligence (MOXAI) for Molecular Subclass Classification of Adult-Type Diffuse Gliomas

    Sep 26, 2026Md Zahangir Alom, Quynh T. Tran, Breuer Alexandar +1Multi-Omics Data IntegrationBrain Tumor Classification

  15. When Explanations Cannot Be Read: Measuring and Correcting SHAP and LIME Rendering for Right-to-Left Languages

    Sep 23, 2026Rameesha Zia, Muhammad Shahid Iqbal MalikExplainable Artificial IntelligenceSHAP Feature Attribution

  16. NeuroRule: Making Black-Box Neural Networks Explainable through Rule-set Evolution

    Sep 22, 2026Tapaswini Kodavanti, Hormoz Shahrzad, Risto MiikkulainenExplainable Artificial IntelligenceNeural Network Interpretability

  17. XSQ-AST: An Explainable Audio Spectrogram Transformer Framework for Localising Synthetic Speech Artifacts

    Sep 21, 2026Ben Heritage, Luca Resti, Mónica Villanueva Aylagas +3Explainable Artificial IntelligenceSpeech Generation Evaluation

  18. Explainable Neuro-Fuzzy Prediction for Trustworthy Decision-Making in Maritime

    Sep 21, 2026Dionisis Kalogeropoulos, Georgia Sovatzidi, Dimitris K. IakovidisExplainable Artificial IntelligencePredictive Maintenance

  19. Adapting Vision-Language Models for Human-Readable XAI in Industrial Object Detection

    Sep 17, 2026Sarvenaz Sardari, Freddy Fernandes, Samarth Yelvande +2Explainable Object DetectionExplainable Artificial Intelligence

  20. Probabilistic Linear Explanations

    Sep 16, 2026Frederic Koriche, Jean-Marie Lagniez, Chi TranExplainable Artificial IntelligenceMixed-Integer QP

  21. Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection

    Sep 15, 2026Jiayi Zhou, David W. Johnston, Brinnae BentExplainable Artificial IntelligenceExplainable Object Detection

  22. PiPS: Post-Hoc Prototypical Explanations for Interpretable Semantic Segmentation

    Sep 15, 2026Miłosz Adamczyk, Tymoteusz Zapala, Piotr Borycki +1Explainable Artificial IntelligencePrototype-Based Explanation

  23. Diversified and Perceptible Counterfactual Examples Leveraging Expert Knowledge

    Sep 14, 2026Akram Bensalem, Fahima Djelil, Marie-Jeanne Lesot +1Explainable Artificial IntelligenceCounterfactual Explanations

  24. Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks

    Sep 12, 2026Tomáš Kolárik, Faezeh Labbaf, Fabrizio Leopardi +3Explainable Artificial IntelligenceNeural Network Interpretability

  25. Trustworthy, Explainable, and Sustainable Decentralized Intelligence for 6G Networks

    Sep 12, 2026Giovanni Perin, Michele Rossi, Enrique Tomás Martínez Beltrán +13Trustworthy AI6G Networks

  26. Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models

    Sep 10, 2026Rodion Krjutškov, Eduard Barbu, Nikos Sakkas +1Explainable Artificial Intelligence

  27. Understanding Operator Attitudes Toward AI-Supported Decision Making in Maritime Operations

    Sep 10, 2026Doreen Jirak, Armeen Saroukanoff, Dirk van RooyAI-Assisted Decision MakingExplainable Artificial Intelligence

  28. X-RACE: XAI-assisted Recurrent neural network Attribution for Channel Estimation

    Sep 10, 2026Abdul Karim Gizzini, Yahia MedjahdiEfficient Neural Network InferenceExplainable Artificial Intelligence

  29. Exploring Second-Order Pattern Recognition in Speaker Recognition

    Sep 10, 2026Yanze Xu, Wenwu Wang, Mark D. PlumbleyExplainable Artificial IntelligenceSpeech Processing