{"total":166,"rows":[{"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":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2103.01890","title":"Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations","created":"2021-03-02","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":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"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":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2111.08446","title":"Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions","created":"2021-11-03","cited_by_count":43,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39,"area":null},{"id":"2204.08945","title":"Missingness Bias in Model Debugging","created":"2022-04-19","cited_by_count":38,"area":null},{"id":"2209.13429","title":"WeightedSHAP: analyzing and improving Shapley based feature attributions","created":"2022-09-27","cited_by_count":36,"area":null},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2111.07668","title":"Fast Axiomatic Attribution for Neural Networks","created":"2021-11-15","cited_by_count":35,"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":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2103.16886","title":"Neural Response Interpretation through the Lens of Critical Pathways","created":"2021-03-31","cited_by_count":32,"area":null},{"id":"2406.07592","title":"MambaLRP: Explaining Selective State Space Sequence Models","created":"2024-06-11","cited_by_count":32,"area":"ssm"},{"id":"2401.12902","title":"Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?","created":"2024-01-23","cited_by_count":31,"area":null},{"id":"2203.12892","title":"Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals","created":"2022-03-24","cited_by_count":30,"area":null},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2206.05075","title":"Diffeomorphic Counterfactuals with Generative Models","created":"2022-06-10","cited_by_count":29,"area":null},{"id":"2106.10649","title":"CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency","created":"2021-06-20","cited_by_count":28,"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":"2103.10415","title":"Refining Language Models with Compositional Explanations","created":"2021-03-18","cited_by_count":27,"area":null},{"id":"2103.14441","title":"Visual Explanations from Spiking Neural Networks using Interspike Intervals","created":"2021-03-26","cited_by_count":27,"area":null},{"id":"2103.13701","title":"ECINN: Efficient Counterfactuals from Invertible Neural Networks","created":"2021-03-25","cited_by_count":26,"area":null},{"id":"2111.05711","title":"Counterfactual Explanations for Models of Code","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2212.08507","title":"Robust Explanation Constraints for Neural Networks","created":"2022-12-16","cited_by_count":24,"area":null},{"id":"2202.12451","title":"Human-Centered Concept Explanations for Neural Networks","created":"2022-02-25","cited_by_count":23,"area":null},{"id":"2107.03178","title":"Levels of explainable artificial intelligence for human-aligned conversational explanations","created":"2021-07-07","cited_by_count":21,"area":null},{"id":"2203.06487","title":"Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?","created":"2022-03-12","cited_by_count":20,"area":null},{"id":"2208.14966","title":"Concept Gradient: Concept-based Interpretation Without Linear Assumption","created":"2022-08-31","cited_by_count":20,"area":null},{"id":"2301.09559","title":"SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]","created":"2023-01-23","cited_by_count":18,"area":null},{"id":"2102.13519","title":"PredDiff: Explanations and Interactions from Conditional Expectations","created":"2021-02-26","cited_by_count":17,"area":null},{"id":"2304.01811","title":"HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation","created":"2023-04-04","cited_by_count":17,"area":null},{"id":"2401.08350","title":"Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models","created":"2024-01-16","cited_by_count":17,"area":null},{"id":"2211.14736","title":"Attribution-based XAI Methods in Computer Vision: A Review","created":"2022-11-27","cited_by_count":16,"area":null},{"id":"2303.14242","title":"IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients","created":"2023-03-24","cited_by_count":16,"area":null},{"id":"2106.07861","title":"Keep CALM and Improve Visual Feature Attribution","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","cited_by_count":15,"area":null},{"id":"2102.01792","title":"A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks","created":"2021-02-02","cited_by_count":14,"area":null},{"id":"2303.14836","title":"Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis","created":"2023-03-26","cited_by_count":14,"area":null},{"id":"2112.14466","title":"Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligence","created":"2021-12-29","cited_by_count":13,"area":null},{"id":"2204.06577","title":"OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data","created":"2022-04-13","cited_by_count":13,"area":null},{"id":"2206.05275","title":"Spatial-temporal Concept based Explanation of 3D ConvNets","created":"2022-06-09","cited_by_count":12,"area":null},{"id":"2212.06872","title":"Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods","created":"2022-12-13","cited_by_count":12,"area":null},{"id":"2403.17409","title":"Neural Clustering based Visual Representation Learning","created":"2024-03-26","cited_by_count":12,"area":null},{"id":"2109.05853","title":"Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions","created":"2021-09-13","cited_by_count":11,"area":null},{"id":"2209.02869","title":"Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps","created":"2022-09-07","cited_by_count":11,"area":null},{"id":"2211.01738","title":"Analysis of a Deep Learning Model for 12-Lead ECG Classification Reveals Learned Features Similar to Diagnostic Criteria","created":"2022-11-03","cited_by_count":11,"area":null},{"id":"2212.13261","title":"Explainable AI for Bioinformatics: Methods, Tools, and Applications","created":"2022-12-25","cited_by_count":11,"area":null},{"id":"2303.01506","title":"Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2408.03915","title":"Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation","created":"2024-08-07","cited_by_count":11,"area":null},{"id":"2312.09783","title":"Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2407.04370","title":"Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2412.17152","title":"Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory","created":"2024-12-22","cited_by_count":10,"area":null},{"id":"2109.01369","title":"Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation","created":"2021-09-03","cited_by_count":9,"area":null},{"id":"2302.02162","title":"AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models","created":"2023-02-04","cited_by_count":9,"area":null},{"id":"2206.04800","title":"Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey","created":"2022-06-07","cited_by_count":8,"area":null},{"id":"2305.15734","title":"On the Impact of Knowledge Distillation for Model Interpretability","created":"2023-05-25","cited_by_count":8,"area":"distill"},{"id":"2407.11910","title":"Benchmarking the Attribution Quality of Vision Models","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2111.03505","title":"Visualizing the Emergence of Intermediate Visual Patterns in DNNs","created":"2021-11-05","cited_by_count":7,"area":null},{"id":"2202.06948","title":"Towards Best Practice of Interpreting Deep Learning Models for EEG-based Brain Computer Interfaces","created":"2022-02-12","cited_by_count":7,"area":null},{"id":"2205.01929","title":"Explain to Not Forget: Defending Against Catastrophic Forgetting with XAI","created":"2022-05-04","cited_by_count":7,"area":null},{"id":"2304.14094","title":"Categorical Foundations of Explainable AI: A Unifying Theory","created":"2023-04-27","cited_by_count":7,"area":null},{"id":"2406.17224","title":"Large Language Models are Interpretable Learners","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2112.04934","title":"Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers","created":"2021-12-09","cited_by_count":6,"area":null},{"id":"2201.09205","title":"Deeply Explain CNN via Hierarchical Decomposition","created":"2022-01-23","cited_by_count":6,"area":null},{"id":"2205.07279","title":"Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection","created":"2022-05-15","cited_by_count":6,"area":null},{"id":"2206.12481","title":"Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2303.17249","title":"Model-agnostic explainable artificial intelligence for object detection in image data","created":"2023-03-30","cited_by_count":6,"area":null},{"id":"2310.09838","title":"Explaining How a Neural Network Play the Go Game and Let People Learn","created":"2023-10-15","cited_by_count":6,"area":null},{"id":"2107.02295","title":"A Review of Explainable Artificial Intelligence in Manufacturing","created":"2021-07-05","cited_by_count":5,"area":null},{"id":"2212.09062","title":"Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint","created":"2022-12-18","cited_by_count":5,"area":null},{"id":"2309.13132","title":"Understanding Calibration of Deep Neural Networks for Medical Image Classification","created":"2023-09-22","cited_by_count":5,"area":null},{"id":"2402.10039","title":"Feature Accentuation: Revealing 'What' Features Respond to in Natural Images","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2406.00539","title":"CONFINE: Conformal Prediction for Interpretable Neural Networks","created":"2024-06-01","cited_by_count":5,"area":null},{"id":"2407.19471","title":"On the Evaluation Consistency of Attribution-based Explanations","created":"2024-07-28","cited_by_count":5,"area":null},{"id":"2104.11691","title":"Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities","created":"2021-04-22","cited_by_count":4,"area":null},{"id":"2106.12074","title":"Reachability Analysis of Convolutional Neural Networks","created":"2021-06-22","cited_by_count":4,"area":null},{"id":"2201.05610","title":"When less is more: Simplifying inputs aids neural network understanding","created":"2022-01-14","cited_by_count":4,"area":null},{"id":"2310.08071","title":"Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2401.10442","title":"Path Choice Matters for Clear Attribution in Path Methods","created":"2024-01-19","cited_by_count":4,"area":null},{"id":"2402.18678","title":"RORA: Robust Free-Text Rationale Evaluation","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2405.12892","title":"Retrievable Domain-Sensitive Feature Memory for Multi-Domain Recommendation","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2406.10117","title":"Trustworthy Artificial Intelligence in the Context of Metrology","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2411.08777","title":"LUDO: Low-Latency Understanding of Deformable Objects using Point Cloud Occupancy Functions","created":"2024-11-13","cited_by_count":4,"area":null},{"id":"2506.17052","title":"From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers","created":"2025-06-20","cited_by_count":4,"area":null},{"id":"2108.06896","title":"Challenges for cognitive decoding using deep learning methods","created":"2021-08-16","cited_by_count":3,"area":null},{"id":"2208.06096","title":"Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insights","created":"2022-08-12","cited_by_count":3,"area":null},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2310.17945","title":"A Comprehensive and Reliable Feature Attribution Method: Double-sided Remove and Reconstruct (DoRaR)","created":"2023-10-27","cited_by_count":3,"area":null},{"id":"2407.10543","title":"Understanding the Dependence of Perception Model Competency on Regions in an Image","created":"2024-07-15","cited_by_count":3,"area":null}],"next_cursor":"100"}