{"total":54,"rows":[{"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":"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":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2104.14995","title":"Interpretable Semantic Photo Geolocation","created":"2021-04-30","cited_by_count":32,"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":"2405.17980","title":"Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering","created":"2024-05-28","cited_by_count":25,"area":null},{"id":"2202.12451","title":"Human-Centered Concept Explanations for Neural Networks","created":"2022-02-25","cited_by_count":23,"area":null},{"id":"2512.18623","title":"LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction","created":"2025-12-21","cited_by_count":15,"area":null},{"id":"2111.12886","title":"Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GAN","created":"2021-11-25","cited_by_count":12,"area":null},{"id":"2409.17073","title":"Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition","created":"2024-09-25","cited_by_count":12,"area":null},{"id":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2307.13850","title":"MAEA: Multimodal Attribution for Embodied AI","created":"2023-07-25","cited_by_count":9,"area":null},{"id":"2311.16120","title":"Sanity checks for patch visualisation in prototype-based image classification","created":"2023-10-25","cited_by_count":8,"area":null},{"id":"2101.10977","title":"Evaluating Input Perturbation Methods for Interpreting CNNs and Saliency Map Comparison","created":"2021-01-26","cited_by_count":7,"area":null},{"id":"2103.10229","title":"Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles","created":"2021-03-18","cited_by_count":6,"area":null},{"id":"2202.11919","title":"Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations","created":"2022-02-24","cited_by_count":6,"area":null},{"id":"2206.06854","title":"On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective","created":"2022-06-14","cited_by_count":6,"area":null},{"id":"2312.05356","title":"Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2102.00951","title":"Counterfactual Generation with Knockoffs","created":"2021-02-01","cited_by_count":4,"area":null},{"id":"2301.08525","title":"Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research","created":"2023-01-20","cited_by_count":4,"area":null},{"id":"2403.09480","title":"What Sketch Explainability Really Means for Downstream Tasks","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2412.17512","title":"BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2109.07804","title":"Detection Accuracy for Evaluating Compositional Explanations of Units","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2302.08508","title":"Sanity checks and improvements for patch visualisation in prototype-based image classification","created":"2023-01-20","cited_by_count":3,"area":null},{"id":"2311.00189","title":"XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision","created":"2023-10-31","cited_by_count":3,"area":null},{"id":"2501.18887","title":"Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability","created":"2025-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2307.09615","title":"Looking deeper into interpretable deep learning in neuroimaging: a comprehensive survey","created":"2023-07-14","cited_by_count":2,"area":null},{"id":"2402.11670","title":"Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry","created":"2024-02-18","cited_by_count":2,"area":null},{"id":"2410.00680","title":"The Conformer Encoder May Reverse the Time Dimension","created":"2024-10-01","cited_by_count":2,"area":null},{"id":"2410.07530","title":"Audio Explanation Synthesis with Generative Foundation Models","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2503.12899","title":"A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2604.06695","title":"Reasoning Fails Where Step Flow Breaks","created":"2026-04-08","cited_by_count":2,"area":"lr"},{"id":"2105.09394","title":"Balancing Robustness and Sensitivity using Feature Contrastive Learning","created":"2021-05-19","cited_by_count":1,"area":null},{"id":"2303.11720","title":"Lidar Line Selection with Spatially-Aware Shapley Value for Cost-Efficient Depth Completion","created":"2023-03-21","cited_by_count":1,"area":null},{"id":"2405.20794","title":"Model Interpretation and Explainability: Towards Creating Transparency in Prediction Models","created":"2024-05-31","cited_by_count":1,"area":null},{"id":"2406.11504","title":"On the Feasibility of Fidelity$^-$ for Graph Pruning","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2407.16010","title":"AIDE: Antithetical, Intent-based, and Diverse Example-Based Explanations","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2504.02016","title":"Fast Fourier Correlation is a Highly Efficient and Accurate Feature Attribution Algorithm from the Perspective of Control Theory and Game Theory","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2108.07081","title":"Toward the Understanding of Deep Text Matching Models for Information Retrieval","created":"2021-08-16","cited_by_count":0,"area":null},{"id":"2108.07714","title":"Harnessing value from data science in business: ensuring explainability and fairness of solutions","created":"2021-08-10","cited_by_count":0,"area":null},{"id":"2211.12702","title":"Evaluating Feature Attribution Methods for Electrocardiogram","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2306.13682","title":"Evaluating the overall sensitivity of saliency-based explanation methods","created":"2023-06-21","cited_by_count":0,"area":null},{"id":"2307.02150","title":"Harmonizing Feature Attributions Across Deep Learning Architectures: Enhancing Interpretability and Consistency","created":"2023-07-05","cited_by_count":0,"area":null},{"id":"2311.14485","title":"Towards Interpretable Classification of Leukocytes based on Deep Learning","created":"2023-11-24","cited_by_count":0,"area":null},{"id":"2312.13234","title":"Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2401.02630","title":"Model-Agnostic Interpretation Framework in Machine Learning: A Comparative Study in NBA Sports","created":"2024-01-05","cited_by_count":0,"area":null},{"id":"2405.13264","title":"Part-based Quantitative Analysis for Heatmaps","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2412.16252","title":"Post-hoc Interpretability Illumination for Scientific Interaction Discovery","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2607.21381","title":"Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.34166","title":"Hidden Activations are not Enough I: Knowledge Matrices as Higher Representations","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.07458","title":"Interpretable Hypergraph Learning via Neural Additive Models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.09844","title":"For Those Who Believe in Faithfulness: Optimizing the Area Under Insertion and Deletion Curves for Ranking Relative Feature Importance","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12060","title":"Look Back, Think Ahead: Visual Memory on Demand for Efficient Multimodal Reasoning","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.12703","title":"Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation","created":"2026-10-08","cited_by_count":0,"area":"ssm"}],"next_cursor":null}