{"total":47,"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":"2102.13620","title":"Towards Robust and Reliable Algorithmic Recourse","created":"2021-02-26","cited_by_count":102,"area":null},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2305.11426","title":"Post Hoc Explanations of Language Models Can Improve Language Models","created":"2023-05-19","cited_by_count":50,"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":"2108.11761","title":"A Framework for Learning Ante-hoc Explainable Models via Concepts","created":"2021-08-25","cited_by_count":45,"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":"2106.09078","title":"Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods","created":"2021-06-16","cited_by_count":36,"area":null},{"id":"2111.01576","title":"Provably efficient, succinct, and precise explanations","created":"2021-11-01","cited_by_count":32,"area":null},{"id":"2108.04990","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","created":"2021-08-11","cited_by_count":30,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2212.08507","title":"Robust Explanation Constraints for Neural Networks","created":"2022-12-16","cited_by_count":24,"area":null},{"id":"2211.16080","title":"Understanding and Enhancing Robustness of Concept-based Models","created":"2022-11-29","cited_by_count":22,"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":"2102.07048","title":"Connecting Interpretability and Robustness in Decision Trees through Separation","created":"2021-02-14","cited_by_count":16,"area":null},{"id":"2208.09967","title":"Inferring Sensitive Attributes from Model Explanations","created":"2022-08-21","cited_by_count":15,"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":"2210.08906","title":"A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities","created":"2022-10-17","cited_by_count":9,"area":null},{"id":"2402.02870","title":"Rethinking Explainable Machine Learning as Applied Statistics","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2207.07072","title":"A Query-Optimal Algorithm for Finding Counterfactuals","created":"2022-07-14","cited_by_count":7,"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":"2307.15361","title":"Confident Feature Ranking","created":"2023-07-28","cited_by_count":6,"area":null},{"id":"2109.07371","title":"Self-learn to Explain Siamese Networks Robustly","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2401.08513","title":"X Hacking: The Threat of Misguided AutoML","created":"2024-01-16","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":"2204.11351","title":"An empirical study of the effect of background data size on the stability of SHapley Additive exPlanations (SHAP) for deep learning models","created":"2022-04-24","cited_by_count":4,"area":null},{"id":"2108.04371","title":"Extending LIME for Business Process Automation","created":"2021-08-09","cited_by_count":3,"area":null},{"id":"2206.12986","title":"Explaining the root causes of unit-level changes","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2312.10534","title":"Rethinking Robustness of Model Attributions","created":"2023-12-16","cited_by_count":3,"area":null},{"id":"2306.03976","title":"Explainable AI using expressive Boolean formulas","created":"2023-06-06","cited_by_count":2,"area":null},{"id":"2310.18496","title":"How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2401.04647","title":"Advancing Ante-Hoc Explainable Models through Generative Adversarial Networks","created":"2024-01-09","cited_by_count":2,"area":null},{"id":"2406.09069","title":"On the Robustness of Global Feature Effect Explanations","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2408.14252","title":"An Evaluation of Explanation Methods for Black-Box Detectors of Machine-Generated Text","created":"2024-08-26","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":"2411.09776","title":"Combining Machine Learning Defenses without Conflicts","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2502.14572","title":"Factor Graph-based Interpretable Neural Networks","created":"2025-02-20","cited_by_count":2,"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":"2404.16495","title":"T-Explainer: A Model-Agnostic Explainability Framework Based on Gradients","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2503.06606","title":"Interpretable Model Drift Detection","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2603.01923","title":"Bound Propagation meets Constraint Simplification: Improving Logic-based XAI for Neural Networks","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2102.07332","title":"Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs","created":"2021-02-15","cited_by_count":0,"area":null},{"id":"2106.02488","title":"Evaluating Local Explanations using White-box Models","created":"2021-06-04","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":"2405.01855","title":"Robust Explainable Recommendation","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2512.18651","title":"Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities","created":"2025-12-21","cited_by_count":0,"area":null}],"next_cursor":null}