{"total":75,"rows":[{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126,"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":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78,"area":null},{"id":"2209.04012","title":"From Shapley Values to Generalized Additive Models and back","created":"2022-09-08","cited_by_count":60,"area":null},{"id":"2407.04846","title":"Amazing Things Come From Having Many Good Models","created":"2024-07-05","cited_by_count":55,"area":null},{"id":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","cited_by_count":32,"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":"2306.15786","title":"An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning","created":"2023-06-27","cited_by_count":25,"area":null},{"id":"2311.15722","title":"GLIME: General, Stable and Local LIME Explanation","created":"2023-11-27","cited_by_count":21,"area":null},{"id":"2305.19101","title":"Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness","created":"2023-05-30","cited_by_count":20,"area":null},{"id":"2303.10139","title":"Distill n' Explain: explaining graph neural networks using simple surrogates","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2307.12344","title":"Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?","created":"2023-07-23","cited_by_count":16,"area":null},{"id":"2307.05902","title":"Stability Guarantees for Feature Attributions with Multiplicative Smoothing","created":"2023-07-12","cited_by_count":14,"area":null},{"id":"2302.03788","title":"Toward a Theory of Causation for Interpreting Neural Code Models","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2404.12862","title":"A Guide to Feature Importance Methods for Scientific Inference","created":"2024-04-19","cited_by_count":11,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2303.00500","title":"Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactuals","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2307.15007","title":"Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability","created":"2023-07-27","cited_by_count":10,"area":null},{"id":"2401.01549","title":"Towards Modeling Uncertainties of Self-explaining Neural Networks via Conformal Prediction","created":"2024-01-03","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":"2401.06465","title":"Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test","created":"2024-01-12","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":"2405.02383","title":"A Fresh Look at Sanity Checks for Saliency Maps","created":"2024-05-03","cited_by_count":8,"area":null},{"id":"2405.13536","title":"Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2303.13299","title":"Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective","created":"2023-03-23","cited_by_count":6,"area":null},{"id":"2405.13474","title":"Why do explanations fail? A typology and discussion on failures in XAI","created":"2024-05-22","cited_by_count":6,"area":null},{"id":"2406.05090","title":"Provably Better Explanations with Optimized Aggregation of Feature Attributions","created":"2024-06-07","cited_by_count":6,"area":null},{"id":"2409.03632","title":"Beyond Model Interpretability: Socio-Structural Explanations in Machine Learning","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2307.07636","title":"Dissenting Explanations: Leveraging Disagreement to Reduce Model Overreliance","created":"2023-07-14","cited_by_count":5,"area":null},{"id":"2312.13033","title":"Explainable artificial intelligence approaches for brain-computer interfaces: a review and design space","created":"2023-12-20","cited_by_count":5,"area":null},{"id":"2406.15613","title":"MOUNTAINEER: Topology-Driven Visual Analytics for Comparing Local Explanations","created":"2024-06-21","cited_by_count":4,"area":null},{"id":"2504.17023","title":"Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency maps","created":"2025-04-23","cited_by_count":4,"area":null},{"id":"2304.12667","title":"Disagreement amongst counterfactual explanations: How transparency can be deceptive","created":"2023-04-25","cited_by_count":3,"area":null},{"id":"2306.06716","title":"On Minimizing the Impact of Dataset Shifts on Actionable Explanations","created":"2023-06-11","cited_by_count":3,"area":null},{"id":"2307.09591","title":"Saliency strikes back: How filtering out high frequencies improves white-box explanations","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2307.13885","title":"Characterizing Data Point Vulnerability via Average-Case Robustness","created":"2023-07-26","cited_by_count":3,"area":null},{"id":"2408.13361","title":"NeurCAM: Interpretable Neural Clustering via Additive Models","created":"2024-08-23","cited_by_count":3,"area":null},{"id":"2303.09545","title":"WebSHAP: Towards Explaining Any Machine Learning Models Anywhere","created":"2023-03-16","cited_by_count":2,"area":null},{"id":"2306.06193","title":"Consistent Explanations in the Face of Model Indeterminacy via Ensembling","created":"2023-06-09","cited_by_count":2,"area":null},{"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":"2308.14115","title":"Situated Natural Language Explanations","created":"2023-08-27","cited_by_count":2,"area":null},{"id":"2405.02583","title":"Explainable Interface for Human-Autonomy Teaming: A Survey","created":"2024-05-04","cited_by_count":2,"area":null},{"id":"2407.08689","title":"Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2409.17774","title":"Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2410.07711","title":"AdaptGrad: Adaptive Sampling to Reduce Noise","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2411.01126","title":"Axiomatic Explainer Globalness via Optimal Transport","created":"2024-11-02","cited_by_count":2,"area":null},{"id":"2508.10490","title":"On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2508.10595","title":"On Spectral Properties of Gradient-based Explanation Methods","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2508.11441","title":"Informative Post-Hoc Explanations Only Exist for Simple Functions","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2604.13258","title":"Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2303.15632","title":"UFO: A unified method for controlling Understandability and Faithfulness Objectives in concept-based explanations for CNNs","created":"2023-03-27","cited_by_count":1,"area":null},{"id":"2307.00873","title":"End-To-End Prediction of Knee Osteoarthritis Progression With Multi-Modal Transformers","created":"2023-07-03","cited_by_count":1,"area":null},{"id":"2307.06963","title":"Is Task-Agnostic Explainable AI a Myth?","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2310.04557","title":"Measuring Information in Text Explanations","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2408.00025","title":"Need of AI in Modern Education: in the Eyes of Explainable AI (xAI)","created":"2024-07-31","cited_by_count":1,"area":null},{"id":"2505.24729","title":"Feature Attribution from First Principles","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2603.00423","title":"An Interpretable Local Editing Model for Counterfactual Medical Image Generation","created":"2026-02-28","cited_by_count":1,"area":null},{"id":"2212.07508","title":"Tensions Between the Proxies of Human Values in AI","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2304.08499","title":"The XAISuite framework and the implications of explanatory system dissonance","created":"2023-04-15","cited_by_count":0,"area":null},{"id":"2311.10811","title":"A novel post-hoc explanation comparison metric and applications","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2401.06890","title":"An Axiomatic Approach to Model-Agnostic Concept Explanations","created":"2024-01-12","cited_by_count":0,"area":null},{"id":"2402.08379","title":"The Duet of Representations and How Explanations Exacerbate It","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2407.00371","title":"Axiomatization of Gradient Smoothing in Neural Networks","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2412.00146","title":"Knowledge-Augmented Explainable and Interpretable Learning for Anomaly Detection and Diagnosis","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2502.07153","title":"Feature Importance Depends on Properties of the Data: Towards Choosing the Correct Explanations for Your Data and Decision Trees based Models","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2504.08919","title":"Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2509.08963","title":"Value bounds and Convergence Analysis for Averages of LRP attributions","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2512.14719","title":"Hybrid Attribution Priors for Explainable and Robust Model Training","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2604.04456","title":"Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.08513","title":"When Fine-Tuning Changes the Evidence: Architecture-Dependent Semantic Drift in Chest X-Ray Explanations","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.05480","title":"GRALIS: Fusing Coalition and Gradient Attribution with Closed-Form Conservation Error and Finite-Sample Guarantees","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2607.14271","title":"Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.16652","title":"Position: Explanation Stability Is a Property of the Model Method Pair, Not the Model","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.14646","title":"iFuzz-Meta: An Interpretable Fuzzy Learning Framework Bridging Top-Down and Bottom-Up Knowledge Integration","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.30397","title":"A Synthetic Ground-Truth Framework for the Evaluation of Explainable AI Methods","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}