{"total":209,"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":"2209.09858","title":"Extremely Simple Activation Shaping for Out-of-Distribution Detection","created":"2022-09-20","cited_by_count":212,"area":null},{"id":"2202.01602","title":"The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":159,"area":null},{"id":"2103.08896","title":"Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation","created":"2021-03-16","cited_by_count":134,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102,"area":null},{"id":"2206.01254","title":"Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations","created":"2022-06-02","cited_by_count":77,"area":null},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73,"area":null},{"id":"2106.12543","title":"Synthetic Benchmarks for Scientific Research in Explainable Machine Learning","created":"2021-06-23","cited_by_count":59,"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":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"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":"2203.06877","title":"Rethinking Stability for Attribution-based Explanations","created":"2022-03-14","cited_by_count":52,"area":null},{"id":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52,"area":null},{"id":"2305.15853","title":"Sequential Integrated Gradients: a simple but effective method for explaining language models","created":"2023-05-25","cited_by_count":52,"area":null},{"id":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48,"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":"2102.10618","title":"Towards the Unification and Robustness of Perturbation and Gradient Based Explanations","created":"2021-02-21","cited_by_count":47,"area":null},{"id":"2212.04871","title":"Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet","created":"2022-12-09","cited_by_count":41,"area":null},{"id":"2205.07277","title":"Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations","created":"2022-05-15","cited_by_count":40,"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":"2110.03109","title":"Consistent Counterfactuals for Deep Models","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2302.07265","title":"The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus","created":"2023-02-14","cited_by_count":37,"area":null},{"id":"2112.11407","title":"Toward Explainable AI for Regression Models","created":"2021-12-21","cited_by_count":31,"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":"2205.07972","title":"Sparse Visual Counterfactual Explanations in Image Space","created":"2022-05-16","cited_by_count":30,"area":null},{"id":"2206.05075","title":"Diffeomorphic Counterfactuals with Generative Models","created":"2022-06-10","cited_by_count":29,"area":null},{"id":"2106.10185","title":"NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights","created":"2021-06-18","cited_by_count":28,"area":null},{"id":"2208.09418","title":"SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability","created":"2022-08-19","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":"2211.13290","title":"SEAT: Stable and Explainable Attention","created":"2022-11-23","cited_by_count":25,"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":"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":"2106.08641","title":"Best of both worlds: local and global explanations with human-understandable concepts","created":"2021-06-16","cited_by_count":22,"area":null},{"id":"2211.05667","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","created":"2022-11-10","cited_by_count":22,"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":"2103.11257","title":"Robust Models Are More Interpretable Because Attributions Look Normal","created":"2021-03-20","cited_by_count":21,"area":null},{"id":"2106.07504","title":"Characterizing the risk of fairwashing","created":"2021-06-14","cited_by_count":21,"area":null},{"id":"2405.09800","title":"Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution","created":"2024-05-16","cited_by_count":21,"area":null},{"id":"2205.15834","title":"Attribution-based Explanations that Provide Recourse Cannot be Robust","created":"2022-05-31","cited_by_count":20,"area":null},{"id":"2208.10605","title":"SoK: Explainable Machine Learning for Computer Security Applications","created":"2022-08-22","cited_by_count":20,"area":null},{"id":"2305.18370","title":"Explainable Brain Age Prediction using coVariance Neural Networks","created":"2023-05-27","cited_by_count":20,"area":null},{"id":"2206.07144","title":"Efficiently Training Low-Curvature Neural Networks","created":"2022-06-14","cited_by_count":19,"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":"2406.03193","title":"Graph Neural Network Explanations are Fragile","created":"2024-06-05","cited_by_count":19,"area":null},{"id":"2108.10346","title":"Explaining Bayesian Neural Networks","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2309.14531","title":"Pixel-Grounded Prototypical Part Networks","created":"2023-09-25","cited_by_count":18,"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":"2301.02437","title":"Valid P-Value for Deep Learning-Driven Salient Region","created":"2023-01-06","cited_by_count":17,"area":null},{"id":"2106.10938","title":"A Game-Theoretic Taxonomy of Visual Concepts in DNNs","created":"2021-06-21","cited_by_count":16,"area":null},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"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":"2201.10528","title":"Explainability in Music Recommender Systems","created":"2022-01-25","cited_by_count":15,"area":null},{"id":"2105.06677","title":"XAI Handbook: Towards a Unified Framework for Explainable AI","created":"2021-05-14","cited_by_count":14,"area":null},{"id":"2211.14860","title":"Foiling Explanations in Deep Neural Networks","created":"2022-11-27","cited_by_count":14,"area":null},{"id":"2304.06715","title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2102.12196","title":"Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis","created":"2021-02-24","cited_by_count":13,"area":null},{"id":"2206.03178","title":"Fooling Explanations in Text Classifiers","created":"2022-06-07","cited_by_count":13,"area":null},{"id":"2405.18217","title":"Understanding Inter-Concept Relationships in Concept-Based Models","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2103.14332","title":"Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation","created":"2021-03-26","cited_by_count":12,"area":null},{"id":"2108.06907","title":"Select Wisely and Explain: Active Learning and Probabilistic Local Post-hoc Explainability","created":"2021-08-16","cited_by_count":12,"area":null},{"id":"2204.04890","title":"Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2206.09875","title":"Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax Audit Models","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2311.17983","title":"Improving Interpretation Faithfulness for Vision Transformers","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2406.10852","title":"IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution","created":"2024-06-16","cited_by_count":12,"area":null},{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2104.12437","title":"Towards Rigorous Interpretations: a Formalisation of Feature Attribution","created":"2021-04-26","cited_by_count":11,"area":null},{"id":"2106.07475","title":"Investigating sanity checks for saliency maps with image and text classification","created":"2021-06-08","cited_by_count":11,"area":null},{"id":"2405.01636","title":"Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Survey","created":"2024-05-02","cited_by_count":11,"area":null},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2307.14239","title":"Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI)","created":"2023-07-26","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":"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":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2206.02868","title":"A Human-Centric Take on Model Monitoring","created":"2022-06-06","cited_by_count":9,"area":null},{"id":"2304.05727","title":"Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks","created":"2023-04-12","cited_by_count":9,"area":null},{"id":"2406.10025","title":"ProtoS-ViT: Visual foundation models for sparse self-explainable classifications","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2407.13281","title":"Auditing Local Explanations is Hard","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2209.01782","title":"\"Is your explanation stable?\": A Robustness Evaluation Framework for Feature Attribution","created":"2022-09-05","cited_by_count":7,"area":null},{"id":"2210.17376","title":"SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability","created":"2022-10-31","cited_by_count":7,"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":"2306.13885","title":"Manipulation Risks in Explainable AI: The Implications of the Disagreement Problem","created":"2023-06-24","cited_by_count":7,"area":null},{"id":"2102.06245","title":"Knowledge Infused Policy Gradients for Adaptive Pandemic Control","created":"2021-02-11","cited_by_count":6,"area":null},{"id":"2104.05467","title":"Understanding Prediction Discrepancies in Machine Learning Classifiers","created":"2021-04-12","cited_by_count":6,"area":null},{"id":"2111.04303","title":"Defense Against Explanation Manipulation","created":"2021-11-08","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":"2210.02419","title":"Boundary-Aware Uncertainty for Feature Attribution Explainers","created":"2022-10-05","cited_by_count":6,"area":null},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2402.03348","title":"Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition","created":"2024-01-25","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":"2101.11702","title":"Better sampling in explanation methods can prevent dieselgate-like deception","created":"2021-01-26","cited_by_count":5,"area":null},{"id":"2109.07371","title":"Self-learn to Explain Siamese Networks Robustly","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2302.05294","title":"MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope","created":"2023-01-08","cited_by_count":5,"area":null}],"next_cursor":"100"}