{"total":141,"rows":[{"id":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125,"area":null},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91,"area":"mechinterp"},{"id":"2311.13594","title":"Labeling Neural Representations with Inverse Recognition","created":"2023-11-22","cited_by_count":32,"area":null},{"id":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2507.07796","title":"Visual Instance-aware Prompt Tuning","created":"2025-07-10","cited_by_count":29,"area":null},{"id":"2401.06654","title":"Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks","created":"2024-01-12","cited_by_count":28,"area":null},{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","cited_by_count":25,"area":null},{"id":"2407.01067","title":"Human-like object concept representations emerge naturally in multimodal large language models","created":"2024-07-01","cited_by_count":25,"area":"mllm"},{"id":"2303.06365","title":"Explainable AI for Time Series via Virtual Inspection Layers","created":"2023-03-11","cited_by_count":23,"area":null},{"id":"2311.16681","title":"Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations","created":"2023-11-28","cited_by_count":22,"area":null},{"id":"2504.19475","title":"Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video","created":"2025-04-28","cited_by_count":21,"area":"mechinterp"},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2410.02331","title":"Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2211.11426","title":"Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations","created":"2022-11-21","cited_by_count":17,"area":null},{"id":"2503.04363","title":"Causally Reliable Concept Bottleneck Models","created":"2025-03-06","cited_by_count":17,"area":null},{"id":"2305.17043","title":"Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2402.18956","title":"WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts","created":"2024-02-29","cited_by_count":14,"area":null},{"id":"2412.01829","title":"Explainable Artificial Intelligence for Medical Applications: A Review","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2408.12568","title":"Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers","created":"2024-08-22","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2303.12942","title":"A Survey on Explainable Artificial Intelligence for Cybersecurity","created":"2023-03-07","cited_by_count":9,"area":null},{"id":"2410.09245","title":"Sui Generis: Large Language Models for Authorship Attribution and Verification in Latin","created":"2024-10-11","cited_by_count":9,"area":null},{"id":"2503.15234","title":"CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2510.11675","title":"FACE: Faithful Automatic Concept Extraction","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2408.17198","title":"Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features","created":"2024-08-30","cited_by_count":7,"area":null},{"id":"2504.09621","title":"Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images","created":"2025-04-13","cited_by_count":7,"area":null},{"id":"2402.12118","title":"Sparse, Efficient and Explainable Data Attribution with DualXDA","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2404.16042","title":"How explainable AI affects human performance: A systematic review of the behavioural consequences of saliency maps","created":"2024-04-03","cited_by_count":6,"area":null},{"id":"2411.05841","title":"FLEXtime: Filterbank learning to explain time series","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2505.20229","title":"From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance","created":"2025-05-26","cited_by_count":6,"area":"mechinterp"},{"id":"2303.10523","title":"Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations","created":"2023-03-19","cited_by_count":5,"area":null},{"id":"2305.14979","title":"Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2310.07534","title":"Human-Centered Evaluation of XAI Methods","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2404.09601","title":"Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2503.15699","title":"Representational Similarity via Interpretable Visual Concepts","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2508.01728","title":"Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations","created":"2025-08-03","cited_by_count":5,"area":"mechinterp"},{"id":"2308.15559","title":"Glocal Explanations of Expected Goal Models in Soccer","created":"2023-08-29","cited_by_count":4,"area":null},{"id":"2406.01649","title":"CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanations","created":"2024-06-03","cited_by_count":4,"area":"diffusion"},{"id":"2410.11896","title":"Study on the Helpfulness of Explainable Artificial Intelligence","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2302.09304","title":"Interpretability in Activation Space Analysis of Transformers: A Focused Survey","created":"2023-01-22","cited_by_count":3,"area":"mechinterp"},{"id":"2306.08933","title":"Towards Interpretability in Audio and Visual Affective Machine Learning: A Review","created":"2023-06-15","cited_by_count":3,"area":null},{"id":"2312.05337","title":"Artificial Neural Nets and the Representation of Human Concepts","created":"2023-12-08","cited_by_count":3,"area":null},{"id":"2401.06122","title":"Manipulating Feature Visualizations with Gradient Slingshots","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2403.17929","title":"Towards Explaining Hypercomplex Neural Networks","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2406.09166","title":"Fine-Grained Domain Generalization with Feature Structuralization","created":"2024-06-13","cited_by_count":3,"area":null},{"id":"2502.16105","title":"NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2503.22399","title":"VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2503.22881","title":"Pairwise Matching of Intermediate Representations for Fine-grained Explainability","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2506.15404","title":"NERO: Explainable Out-of-Distribution Detection with Neuron-level Relevance","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2510.27413","title":"Atlas-Alignment: Making Interpretability Transferable Across Language Models","created":"2025-10-31","cited_by_count":3,"area":"mechinterp"},{"id":"2308.12053","title":"Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2310.11450","title":"Explaining Deep Neural Networks for Bearing Fault Detection with Vibration Concepts","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2402.14728","title":"The European Commitment to Human-Centered Technology: The Integral Role of HCI in the EU AI Act's Success","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2403.15603","title":"Forward Learning for Gradient-based Black-box Saliency Map Generation","created":"2024-03-22","cited_by_count":2,"area":null},{"id":"2404.10433","title":"Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2404.18316","title":"Position: Do Not Explain Vision Models Without Context","created":"2024-04-28","cited_by_count":2,"area":null},{"id":"2405.17523","title":"Locally Testing Model Detections for Semantic Global Concepts","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2408.02379","title":"The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2411.15626","title":"Aligning Generalisation Between Humans and Machines","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2412.07313","title":"FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2412.15114","title":"Towards Friendly AI: A Comprehensive Review and New Perspectives on Human-AI Alignment","created":"2024-12-19","cited_by_count":2,"area":null},{"id":"2501.13818","title":"Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2504.02685","title":"STOOD-X methodology: using statistical nonparametric test for OOD Detection Large-Scale datasets enhanced with explainability","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2505.06123","title":"Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomena","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2506.05887","title":"A three-Level Framework for LLM-Enhanced eXplainable AI: From technical explanations to natural language","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2506.14775","title":"See What I Mean? CUE: A Cognitive Model of Understanding Explanations","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2507.11099","title":"A Survey on Interpretability in Visual Recognition","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2511.07974","title":"Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2606.00557","title":"Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2608.12036","title":"Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2302.03180","title":"Understanding User Preferences in Explainable Artificial Intelligence: A Survey and a Mapping Function Proposal","created":"2023-02-07","cited_by_count":1,"area":null},{"id":"2304.05895","title":"Towards Understanding How Data Augmentation Works with Imbalanced Data","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2310.03457","title":"A Quantitatively Interpretable Model for Alzheimer's Disease Prediction Using Deep Counterfactuals","created":"2023-10-05","cited_by_count":1,"area":null},{"id":"2311.10933","title":"Representing visual classification as a linear combination of words","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2312.08063","title":"Estimation of Concept Explanations Should be Uncertainty Aware","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2401.10044","title":"Deep spatial context: when attention-based models meet spatial regression","created":"2024-01-18","cited_by_count":1,"area":null},{"id":"2404.09768","title":"Contrastive Pretraining for Visual Concept Explanations of Socioeconomic Outcomes","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2404.18736","title":"Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2405.01661","title":"When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReX","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2405.10552","title":"Data Science Principles for Interpretable and Explainable AI","created":"2024-05-17","cited_by_count":1,"area":null},{"id":"2406.11882","title":"Applications of Explainable artificial intelligence in Earth system science","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2408.02123","title":"FovEx: Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2409.01610","title":"Decompose the model: Mechanistic interpretability in image models with Generalized Integrated Gradients (GIG)","created":"2024-09-03","cited_by_count":1,"area":"mechinterp"},{"id":"2409.09378","title":"Prevailing Research Areas for Music AI in the Era of Foundation Models","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2410.05114","title":"Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2410.16662","title":"Visual Question Answering in Ophthalmology: A Progressive and Practical Perspective","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2503.05522","title":"Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations","created":"2025-03-07","cited_by_count":1,"area":"mechinterp"},{"id":"2504.08602","title":"On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2504.13140","title":"PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2505.15516","title":"Explainable embeddings with Distance Explainer","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.20293","title":"Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.02092","title":"Towards Better Generalization and Interpretability in Unsupervised Concept-Based Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2509.23849","title":"CE-FAM: Concept-Based Explanation via Fusion of Activation Maps","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2605.00474","title":"From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models","created":"2026-05-01","cited_by_count":1,"area":"mechinterp"}],"next_cursor":"100"}