{"total":159,"rows":[{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126,"area":null},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90,"area":"lr"},{"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":"2207.04154","title":"TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations","created":"2022-07-08","cited_by_count":66,"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":"2305.11426","title":"Post Hoc Explanations of Language Models Can Improve Language Models","created":"2023-05-19","cited_by_count":50,"area":null},{"id":"2211.00541","title":"Logic-Based Explainability in Machine Learning","created":"2022-10-24","cited_by_count":48,"area":null},{"id":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43,"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":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2206.01136","title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","created":"2022-06-02","cited_by_count":33,"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":"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":"2404.02233","title":"Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models","created":"2024-04-02","cited_by_count":22,"area":null},{"id":"2206.05487","title":"Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena","created":"2022-06-11","cited_by_count":21,"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":"2309.14531","title":"Pixel-Grounded Prototypical Part Networks","created":"2023-09-25","cited_by_count":18,"area":null},{"id":"2401.10640","title":"A comprehensive study on fidelity metrics for XAI","created":"2024-01-19","cited_by_count":16,"area":null},{"id":"2305.17043","title":"Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2504.12691","title":"Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2205.04559","title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","created":"2022-05-09","cited_by_count":13,"area":null},{"id":"2304.11218","title":"Explainability in AI Policies: A Critical Review of Communications, Reports, Regulations, and Standards in the EU, US, and UK","created":"2023-04-20","cited_by_count":13,"area":null},{"id":"2205.14772","title":"Unfooling Perturbation-Based Post Hoc Explainers","created":"2022-05-29","cited_by_count":12,"area":null},{"id":"2307.00364","title":"The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations","created":"2023-07-01","cited_by_count":12,"area":null},{"id":"2205.00202","title":"Explainable Artificial Intelligence for Bayesian Neural Networks: Towards trustworthy predictions of ocean dynamics","created":"2022-04-30","cited_by_count":11,"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":"2404.12862","title":"A Guide to Feature Importance Methods for Scientific Inference","created":"2024-04-19","cited_by_count":11,"area":null},{"id":"2205.08452","title":"A Psychological Theory of Explainability","created":"2022-05-17","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":"2310.18526","title":"Sample based Explanations via Generalized Representers","created":"2023-10-27","cited_by_count":10,"area":null},{"id":"2303.17707","title":"Why is plausibility surprisingly problematic as an XAI criterion?","created":"2023-03-30","cited_by_count":9,"area":null},{"id":"2310.05797","title":"In-Context Explainers: Harnessing LLMs for Explaining Black Box Models","created":"2023-10-09","cited_by_count":9,"area":"lr"},{"id":"2402.02933","title":"Intrinsic User-Centric Interpretability through Global Mixture of Experts","created":"2024-02-05","cited_by_count":9,"area":"moe"},{"id":"2402.02870","title":"Rethinking Explainable Machine Learning as Applied Statistics","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2409.00743","title":"Interpretable Clustering: A Survey","created":"2024-09-01","cited_by_count":8,"area":null},{"id":"2410.22598","title":"Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2203.03668","title":"A Typology for Exploring the Mitigation of Shortcut Behavior","created":"2022-03-04","cited_by_count":7,"area":null},{"id":"2210.03047","title":"Conditional Feature Importance for Mixed Data","created":"2022-10-06","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":"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":"2311.07763","title":"The Disagreement Problem in Faithfulness Metrics","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2404.11330","title":"Toward Understanding the Disagreement Problem in Neural Network Feature Attribution","created":"2024-04-17","cited_by_count":6,"area":null},{"id":"2507.14744","title":"Beyond the Single-Best Model: Rashomon Partial Dependence Profile for Trustworthy Explanations in AutoML","created":"2025-07-19","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":"2310.03466","title":"The Blame Problem in Evaluating Local Explanations, and How to Tackle it","created":"2023-10-05","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":"2407.19471","title":"On the Evaluation Consistency of Attribution-based Explanations","created":"2024-07-28","cited_by_count":5,"area":null},{"id":"2601.12654","title":"Explanation Multiplicity in SHAP: Characterization and Assessment","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2207.00007","title":"\"Explanation\" is Not a Technical Term: The Problem of Ambiguity in XAI","created":"2022-06-27","cited_by_count":4,"area":null},{"id":"2310.05619","title":"Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods","created":"2023-10-09","cited_by_count":4,"area":null},{"id":"2310.07882","title":"The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research","created":"2023-10-11","cited_by_count":4,"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":"2412.05592","title":"From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation","created":"2024-12-07","cited_by_count":4,"area":null},{"id":"2501.13887","title":"What Does an Audio Deepfake Detector Focus on? A Study in the Time Domain","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2506.20209","title":"Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2601.22359","title":"The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples","created":"2026-01-29","cited_by_count":4,"area":"safety"},{"id":"2207.11231","title":"Learning Unsupervised Hierarchies of Audio Concepts","created":"2022-07-21","cited_by_count":3,"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":"2310.05484","title":"IDTraffickers: An Authorship Attribution Dataset to link and connect Potential Human-Trafficking Operations on Text Escort Advertisements","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2310.06514","title":"AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments","created":"2023-10-10","cited_by_count":3,"area":null},{"id":"2403.19424","title":"The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement","created":"2024-03-28","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":"2502.09849","title":"A Survey on Human-Centered Evaluation of Explainable AI Methods in Clinical Decision Support Systems","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2504.16148","title":"Towards responsible AI for education: Hybrid human-AI to confront the Elephant in the room","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2505.01198","title":"Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods","created":"2025-05-02","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":"2304.03368","title":"From Explanation to Action: An End-to-End Human-in-the-loop Framework for Anomaly Reasoning and Management","created":"2023-04-06","cited_by_count":2,"area":null},{"id":"2304.14606","title":"Algorithmic Recourse with Missing Values","created":"2023-04-28","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":"2310.08495","title":"Characterizing climate pathways using feature importance on echo state networks","created":"2023-10-12","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":"2404.16534","title":"SIDEs: Separating Idealization from Deceptive Explanations in xAI","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2406.07820","title":"Are Objective Explanatory Evaluation metrics Trustworthy? An Adversarial Analysis","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2411.12643","title":"DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models","created":"2024-11-19","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":"2509.14830","title":"ProtoMedX: Towards Explainable Multi-Modal Prototype Learning for Bone Health Classification","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2606.07607","title":"Position: Genomic Model Research Must Move Beyond Anecdotal Evaluation of Interpretability Methods","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2607.14123","title":"Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods","created":"2026-06-18","cited_by_count":2,"area":"mechinterp"},{"id":"2607.18921","title":"Circuit Claims Depend on What Is Extracted and How It Is Compared","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2205.06234","title":"SIBILA: A novel interpretable ensemble of general-purpose machine learning models applied to medical contexts","created":"2022-05-12","cited_by_count":1,"area":null},{"id":"2207.01565","title":"Fidelity of Ensemble Aggregation for Saliency Map Explanations using Bayesian Optimization Techniques","created":"2022-07-04","cited_by_count":1,"area":null},{"id":"2208.12814","title":"Interpretable (not just posthoc-explainable) medical claims modeling for discharge placement to prevent avoidable all-cause readmissions or death","created":"2022-08-28","cited_by_count":1,"area":null},{"id":"2301.03774","title":"How Data Scientists Review the Scholarly Literature","created":"2023-01-10","cited_by_count":1,"area":null},{"id":"2302.07185","title":"When mitigating bias is unfair: multiplicity and arbitrariness in algorithmic group fairness","created":"2023-02-14","cited_by_count":1,"area":null},{"id":"2302.09190","title":"Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2302.11577","title":"Explainable AI does not provide the explanations end-users are asking for","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2303.01704","title":"Feature Importance Disparities for Data Bias Investigations","created":"2023-03-03","cited_by_count":1,"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":"2304.09981","title":"Interpretable (not just posthoc-explainable) heterogeneous survivor bias-corrected treatment effects for assignment of postdischarge interventions to prevent readmissions","created":"2023-04-19","cited_by_count":1,"area":null},{"id":"2306.11985","title":"Evaluation of Popular XAI Applied to Clinical Prediction Models: Can They be Trusted?","created":"2023-06-21","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":"2308.08949","title":"A Dual-Perspective Approach to Evaluating Feature Attribution Methods","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2312.09529","title":"Can Physician Judgment Enhance Model Trustworthiness? A Case Study on Predicting Pathological Lymph Nodes in Rectal Cancer","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2402.00347","title":"Diverse Explanations From Data-Driven and Domain-Driven Perspectives in the Physical Sciences","created":"2024-02-01","cited_by_count":1,"area":null},{"id":"2404.10387","title":"CNN-based explanation ensembling for dataset, representation and explanations evaluation","created":"2024-04-16","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":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null}],"next_cursor":"100"}