{"total":55,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2202.06861","title":"Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond","created":"2022-02-14","cited_by_count":171,"area":null},{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126,"area":null},{"id":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"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":"2208.09418","title":"SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability","created":"2022-08-19","cited_by_count":28,"area":null},{"id":"2409.16756","title":"Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics","created":"2024-09-25","cited_by_count":16,"area":null},{"id":"2303.01538","title":"Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2310.01685","title":"A Framework for Interpretability in Machine Learning for Medical Imaging","created":"2023-10-02","cited_by_count":9,"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":"2402.02933","title":"Intrinsic User-Centric Interpretability through Global Mixture of Experts","created":"2024-02-05","cited_by_count":9,"area":"moe"},{"id":"2405.02383","title":"A Fresh Look at Sanity Checks for Saliency Maps","created":"2024-05-03","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":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2311.01732","title":"Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models","created":"2023-11-03","cited_by_count":7,"area":"mechinterp"},{"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":"2206.04740","title":"XAudit : A Theoretical Look at Auditing with Explanations","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2601.20815","title":"GNN Explanations that do not Explain and How to find Them","created":"2026-01-28","cited_by_count":5,"area":null},{"id":"2301.13445","title":"A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2406.01274","title":"Expected Grad-CAM: Towards gradient faithfulness","created":"2024-06-03","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":"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":"2408.16395","title":"IBO: Inpainting-Based Occlusion to Enhance Explainable Artificial Intelligence Evaluation in Histopathology","created":"2024-08-29","cited_by_count":3,"area":null},{"id":"2311.01605","title":"Faithful and Robust Local Interpretability for Textual Predictions","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2406.00116","title":"A Sim2Real Approach for Identifying Task-Relevant Properties in Interpretable Machine Learning","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2406.00611","title":"DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation","created":"2024-06-02","cited_by_count":2,"area":null},{"id":"2411.15605","title":"GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2502.03773","title":"ExpProof : Operationalizing Explanations for Confidential Models with ZKPs","created":"2025-02-06","cited_by_count":2,"area":null},{"id":"2505.02828","title":"Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Review","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2507.12900","title":"Knowing What You Cannot Explain: Learning to Reject Low-Quality Explanations","created":"2025-07-17","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":"2602.18160","title":"Unifying Formal Explanations: A Complexity-Theoretic Perspective","created":"2026-02-20","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":"2412.09311","title":"Advancing Attribution-Based Neural Network Explainability through Relative Absolute Magnitude Layer-Wise Relevance Propagation and Multi-Component Evaluation","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2412.20798","title":"Reconciling Privacy and Explainability in High-Stakes: A Systematic Inquiry","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2503.23111","title":"How to safely discard features based on aggregate SHAP values","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2504.08552","title":"Towards an Evaluation Framework for Explainable Artificial Intelligence Systems for Health and Well-being","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2504.12197","title":"Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2504.20667","title":"Explanations Go Linear: Post-hoc Explainability for Tabular Data with Interpretable Meta-Encoding","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2507.04528","title":"Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligence","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2502.02786","title":"When Machine Learning Gets Personal: Evaluating Prediction and Explanation","created":"2025-02-05","cited_by_count":0,"area":null},{"id":"2502.15403","title":"Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2508.03586","title":"DeepFaith: A Domain-Free and Model-Agnostic Unified Framework for Highly Faithful Explanations","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2508.18154","title":"Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability","created":"2025-08-25","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":"2511.11922","title":"Additive Large Language Models for Semi-Structured Text","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2512.07578","title":"$\\phi$-Table: A Statistical Explanation for Global SHAP","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.04378","title":"Aligned explanations in neural networks","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2602.11920","title":"Learning Conditional Averages","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2605.14550","title":"Multi-Dimensional Model Integrity and Responsibility Assessment Index and Scoring Framework","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.24742","title":"Aligning Molecular Graph Explanations with Chemical Identity via InChIfied Invariants","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.16786","title":"We Need Explanation Cards to Connect Explanation Algorithms to the Real World","created":"2026-06-15","cited_by_count":0,"area":null}],"next_cursor":null}