{"total":737,"rows":[{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336,"area":"mllm"},{"id":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312,"area":null},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195,"area":null},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"area":null},{"id":"2107.10912","title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","created":"2021-07-22","cited_by_count":147,"area":null},{"id":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"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":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2306.01574","title":"Probabilistic Concept Bottleneck Models","created":"2023-06-02","cited_by_count":101,"area":null},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100,"area":null},{"id":"2203.15046","title":"AUC Maximization in the Era of Big Data and AI: A Survey","created":"2022-03-28","cited_by_count":100,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2112.02902","title":"Interpretable Image Classification with Differentiable Prototypes Assignment","created":"2021-12-06","cited_by_count":97,"area":null},{"id":"2112.00911","title":"ProtGNN: Towards Self-Explaining Graph Neural Networks","created":"2021-12-02","cited_by_count":96,"area":null},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91,"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":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88,"area":null},{"id":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88,"area":null},{"id":"2210.11584","title":"Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations","created":"2022-10-20","cited_by_count":85,"area":null},{"id":"2111.02398","title":"Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods","created":"2021-11-01","cited_by_count":83,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2202.01459","title":"Concept Bottleneck Model with Additional Unsupervised Concepts","created":"2022-02-03","cited_by_count":79,"area":null},{"id":"2203.15636","title":"Diffusion Models for Counterfactual Explanations","created":"2022-03-29","cited_by_count":79,"area":"diffusion"},{"id":"2103.10663","title":"XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations","created":"2021-03-19","cited_by_count":73,"area":null},{"id":"2112.11561","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","created":"2021-12-21","cited_by_count":73,"area":"driving"},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73,"area":null},{"id":"2103.12308","title":"IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography","created":"2021-03-23","cited_by_count":72,"area":null},{"id":"2405.11643","title":"Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology","created":"2024-05-19","cited_by_count":72,"area":null},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2105.02968","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","created":"2021-05-05","cited_by_count":65,"area":null},{"id":"2210.07147","title":"Global Explainability of GNNs via Logic Combination of Learned Concepts","created":"2022-10-13","cited_by_count":65,"area":null},{"id":"2101.09824","title":"Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs","created":"2021-01-24","cited_by_count":64,"area":null},{"id":"2208.10431","title":"ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition","created":"2022-08-22","cited_by_count":63,"area":null},{"id":"2210.03735","title":"\"Help Me Help the AI\": Understanding How Explainability Can Support Human-AI Interaction","created":"2022-10-02","cited_by_count":63,"area":null},{"id":"2305.19951","title":"Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts","created":"2023-05-31","cited_by_count":63,"area":null},{"id":"2104.07411","title":"NICE: An Algorithm for Nearest Instance Counterfactual Explanations","created":"2021-04-15","cited_by_count":62,"area":null},{"id":"2106.12543","title":"Synthetic Benchmarks for Scientific Research in Explainable Machine Learning","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59,"area":null},{"id":"2209.11222","title":"Concept Activation Regions: A Generalized Framework For Concept-Based Explanations","created":"2022-09-22","cited_by_count":57,"area":null},{"id":"2104.00032","title":"Convolutional Dynamic Alignment Networks for Interpretable Classifications","created":"2021-03-31","cited_by_count":54,"area":null},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"area":null},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52,"area":null},{"id":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52,"area":null},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","cited_by_count":50,"area":null},{"id":"2308.06248","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","created":"2023-08-11","cited_by_count":50,"area":null},{"id":"2304.10131","title":"Learning Bottleneck Concepts in Image Classification","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2207.09615","title":"Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability","created":"2022-07-20","cited_by_count":46,"area":null},{"id":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44,"area":null},{"id":"2108.12204","title":"This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation","created":"2021-08-27","cited_by_count":43,"area":null},{"id":"2106.00305","title":"Independent Prototype Propagation for Zero-Shot Compositionality","created":"2021-06-01","cited_by_count":42,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2201.03014","title":"Glance and Focus Networks for Dynamic Visual Recognition","created":"2022-01-09","cited_by_count":41,"area":null},{"id":"2306.01128","title":"Learning Transformer Programs","created":"2023-06-01","cited_by_count":41,"area":"mechinterp"},{"id":"2111.09094","title":"STEEX: Steering Counterfactual Explanations with Semantics","created":"2021-11-17","cited_by_count":40,"area":null},{"id":"2201.13291","title":"Metrics for saliency map evaluation of deep learning explanation methods","created":"2022-01-31","cited_by_count":40,"area":null},{"id":"2204.13738","title":"One Model to Synthesize Them All: Multi-contrast Multi-scale Transformer for Missing Data Imputation","created":"2022-04-28","cited_by_count":40,"area":null},{"id":"2208.00780","title":"Visual correspondence-based explanations improve AI robustness and human-AI team accuracy","created":"2022-07-26","cited_by_count":39,"area":null},{"id":"2102.02515","title":"HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks","created":"2021-02-04","cited_by_count":38,"area":null},{"id":"2209.11799","title":"Augmenting Interpretable Models with LLMs during Training","created":"2022-09-23","cited_by_count":38,"area":null},{"id":"2301.04011","title":"Learning Support and Trivial Prototypes for Interpretable Image Classification","created":"2023-01-08","cited_by_count":38,"area":null},{"id":"2212.05946","title":"Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks","created":"2022-12-12","cited_by_count":37,"area":null},{"id":"2310.18589","title":"This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations","created":"2023-10-28","cited_by_count":36,"area":null},{"id":"2202.10553","title":"Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis","created":"2022-02-16","cited_by_count":35,"area":null},{"id":"2211.15115","title":"Generalized Category Discovery with Decoupled Prototypical Network","created":"2022-11-28","cited_by_count":35,"area":null},{"id":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2210.08151","title":"ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model","created":"2022-10-15","cited_by_count":34,"area":null},{"id":"2303.13995","title":"LINe: Out-of-Distribution Detection by Leveraging Important Neurons","created":"2023-03-24","cited_by_count":34,"area":null},{"id":"2203.15064","title":"Cycle-Consistent Counterfactuals by Latent Transformations","created":"2022-03-28","cited_by_count":33,"area":null},{"id":"2301.12276","title":"ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts","created":"2023-01-28","cited_by_count":33,"area":null},{"id":"2401.14142","title":"Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations","created":"2024-01-25","cited_by_count":33,"area":null},{"id":"2201.09051","title":"On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations","created":"2022-01-22","cited_by_count":32,"area":null},{"id":"2205.04766","title":"Explainable Deep Learning Methods in Medical Image Classification: A Survey","created":"2022-05-10","cited_by_count":32,"area":null},{"id":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31,"area":null},{"id":"2111.10934","title":"Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretability","created":"2021-11-22","cited_by_count":28,"area":null},{"id":"2112.10526","title":"NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems","created":"2021-12-20","cited_by_count":28,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2211.12380","title":"OCTET: Object-aware Counterfactual Explanations","created":"2022-11-22","cited_by_count":28,"area":null},{"id":"2304.13188","title":"TABLET: Learning From Instructions For Tabular Data","created":"2023-04-25","cited_by_count":28,"area":null},{"id":"2309.07944","title":"Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach","created":"2023-09-14","cited_by_count":28,"area":null},{"id":"2410.08417","title":"Bilinear MLPs enable weight-based mechanistic interpretability","created":"2024-10-10","cited_by_count":28,"area":"mechinterp"},{"id":"2503.23283","title":"Language Guided Concept Bottleneck Models for Interpretable Continual Learning","created":"2025-03-30","cited_by_count":28,"area":null},{"id":"2210.16966","title":"Interpretable Geometric Deep Learning via Learnable Randomness Injection","created":"2022-10-30","cited_by_count":27,"area":null},{"id":"2303.00652","title":"Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science","created":"2023-03-01","cited_by_count":27,"area":null},{"id":"2308.08162","title":"Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations","created":"2023-08-16","cited_by_count":27,"area":null},{"id":"2504.12880","title":"Can Masked Autoencoders Also Listen to Birds?","created":"2025-04-17","cited_by_count":26,"area":null},{"id":"2508.04665","title":"Perch 2.0: The Bittern Lesson for Bioacoustics","created":"2025-08-06","cited_by_count":26,"area":null},{"id":"2205.14108","title":"Scalable Interpretability via Polynomials","created":"2022-05-27","cited_by_count":25,"area":null},{"id":"2410.20722","title":"Interpretable Image Classification with Adaptive Prototype-based Vision Transformers","created":"2024-10-28","cited_by_count":25,"area":null},{"id":"2502.06755","title":"Interpretable and Testable Vision Features via Sparse Autoencoders","created":"2025-02-10","cited_by_count":25,"area":"mechinterp"},{"id":"2112.02290","title":"Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations","created":"2021-12-04","cited_by_count":24,"area":null}],"next_cursor":"100"}