{"total":72,"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":"2311.16424","title":"Manifold Preserving Guided Diffusion","created":"2023-11-28","cited_by_count":157,"area":"diffusion"},{"id":"2207.07068","title":"Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey","created":"2022-07-14","cited_by_count":125,"area":null},{"id":"2106.02666","title":"Counterfactual Explanations Can Be Manipulated","created":"2021-06-04","cited_by_count":113,"area":null},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55,"area":null},{"id":"2201.10295","title":"Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts","created":"2022-01-25","cited_by_count":53,"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":"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":"2103.02354","title":"Evaluating Robustness of Counterfactual Explanations","created":"2021-03-03","cited_by_count":41,"area":null},{"id":"2111.00358","title":"A Survey on the Robustness of Feature Importance and Counterfactual Explanations","created":"2021-10-30","cited_by_count":39,"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":"2206.05075","title":"Diffeomorphic Counterfactuals with Generative Models","created":"2022-06-10","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":"2110.09253","title":"A Sociotechnical View of Algorithmic Fairness","created":"2021-09-27","cited_by_count":24,"area":null},{"id":"2212.08507","title":"Robust Explanation Constraints for Neural Networks","created":"2022-12-16","cited_by_count":24,"area":null},{"id":"2111.08230","title":"Selective Ensembles for Consistent Predictions","created":"2021-11-16","cited_by_count":23,"area":null},{"id":"2106.07504","title":"Characterizing the risk of fairwashing","created":"2021-06-14","cited_by_count":21,"area":null},{"id":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20,"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":"2306.07462","title":"On the Robustness of Removal-Based Feature Attributions","created":"2023-06-12","cited_by_count":19,"area":null},{"id":"2102.13519","title":"PredDiff: Explanations and Interactions from Conditional Expectations","created":"2021-02-26","cited_by_count":17,"area":null},{"id":"2106.04631","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","created":"2021-06-08","cited_by_count":17,"area":null},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2310.13007","title":"A Critical Survey on Fairness Benefits of Explainable AI","created":"2023-10-15","cited_by_count":16,"area":null},{"id":"2207.06154","title":"On the Robustness of Bayesian Neural Networks to Adversarial Attacks","created":"2022-07-13","cited_by_count":12,"area":null},{"id":"2109.03952","title":"Attributing Fair Decisions with Attention Interventions","created":"2021-09-08","cited_by_count":10,"area":null},{"id":"2308.14272","title":"Goodhart's Law Applies to NLP's Explanation Benchmarks","created":"2023-08-28","cited_by_count":10,"area":null},{"id":"2110.07120","title":"Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2301.04041","title":"Manifold Restricted Interventional Shapley Values","created":"2023-01-10","cited_by_count":9,"area":null},{"id":"2206.14004","title":"On the amplification of security and privacy risks by post-hoc explanations in machine learning models","created":"2022-06-28","cited_by_count":8,"area":null},{"id":"2402.02870","title":"Rethinking Explainable Machine Learning as Applied Statistics","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2306.07397","title":"Adversarial Attacks on the Interpretation of Neuron Activation Maximization","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2104.05467","title":"Understanding Prediction Discrepancies in Machine Learning Classifiers","created":"2021-04-12","cited_by_count":6,"area":null},{"id":"2310.16316","title":"Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2505.04796","title":"Robust ML Auditing using Prior Knowledge","created":"2025-05-07","cited_by_count":6,"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":"2406.14349","title":"When Can You Trust Your Explanations? A Robustness Analysis on Feature Importances","created":"2024-06-20","cited_by_count":5,"area":null},{"id":"2108.05390","title":"Seven challenges for harmonizing explainability requirements","created":"2021-08-11","cited_by_count":4,"area":null},{"id":"2204.09498","title":"Backdooring Explainable Machine Learning","created":"2022-04-20","cited_by_count":4,"area":null},{"id":"2211.15900","title":"Towards More Robust Interpretation via Local Gradient Alignment","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2311.17228","title":"Survey on AI Ethics: A Socio-technical Perspective","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2202.11797","title":"Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four","created":"2022-02-23","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":"2401.06122","title":"Manipulating Feature Visualizations with Gradient Slingshots","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2503.08636","title":"Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2505.22973","title":"EquiReg: Equivariance Regularized Diffusion for Inverse Problems","created":"2025-05-29","cited_by_count":3,"area":"diffusion"},{"id":"2403.03773","title":"Verified Training for Counterfactual Explanation Robustness under Data Shift","created":"2024-03-06","cited_by_count":2,"area":null},{"id":"2409.05208","title":"Influence-based Attributions can be Manipulated","created":"2024-09-08","cited_by_count":2,"area":null},{"id":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","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":"2102.11010","title":"Resilience of Bayesian Layer-Wise Explanations under Adversarial Attacks","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2201.12143","title":"Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning","created":"2022-01-28","cited_by_count":1,"area":null},{"id":"2401.03128","title":"Manifold-based Shapley for SAR Recognization Network Explanation","created":"2024-01-06","cited_by_count":1,"area":null},{"id":"2505.11060","title":"CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2506.01594","title":"Selecting for Less Discriminatory Algorithms: A Relational Search Framework for Navigating Fairness-Accuracy Trade-offs in Practice","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2507.19408","title":"On Arbitrary Predictions from Equally Valid Models","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2608.04365","title":"Manipulation-Proof Oblivious Audits against Deceptive Model Providers","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2306.04505","title":"Hardness of Deceptive Certificate Selection","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2309.01780","title":"Measuring, Interpreting, and Improving Fairness of Algorithms using Causal Inference and Randomized Experiments","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2311.13454","title":"Explaining high-dimensional text classifiers","created":"2023-11-22","cited_by_count":0,"area":null},{"id":"2403.16569","title":"Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoors","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2406.01365","title":"From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2510.02996","title":"Onto-Epistemological Analysis of AI Explanations","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2606.28391","title":"Few-class Fidelity: Evaluating Explanations of Real-conditions CNN classifiers with Optimized Perturbations","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.31394","title":"Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.36970","title":"Equally Good, Yet Different: Benchmarking Rashomon sets in AutoML packages","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.15850","title":"What Do Sparse Autoencoder Feature Discovery Scores Identify? From Activations to Interventions","created":"2026-10-11","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}