{"total":74,"rows":[{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63,"area":null},{"id":"2402.10086","title":"Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2306.05724","title":"Explaining Predictive Uncertainty with Information Theoretic Shapley Values","created":"2023-06-09","cited_by_count":36,"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":"2312.01429","title":"Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars","created":"2023-12-03","cited_by_count":30,"area":null},{"id":"2405.03875","title":"Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits","created":"2024-05-06","cited_by_count":29,"area":null},{"id":"2502.07586","title":"We Can't Understand AI Using our Existing Vocabulary","created":"2025-02-11","cited_by_count":25,"area":null},{"id":"2406.01317","title":"The Interpretable and Effective Graph Neural Additive Networks","created":"2024-06-03","cited_by_count":20,"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":"2307.05902","title":"Stability Guarantees for Feature Attributions with Multiplicative Smoothing","created":"2023-07-12","cited_by_count":14,"area":null},{"id":"2410.16638","title":"LLMScan: Causal Scan for LLM Misbehavior Detection","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2504.11609","title":"Towards Interpretable Deep Generative Models via Causal Representation Learning","created":"2025-04-15","cited_by_count":13,"area":null},{"id":"2404.06647","title":"From Protoscience to Epistemic Monoculture: How Benchmarking Set the Stage for the Deep Learning Revolution","created":"2024-04-09","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":"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":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2310.18526","title":"Sample based Explanations via Generalized Representers","created":"2023-10-27","cited_by_count":10,"area":null},{"id":"2504.13787","title":"Probabilistic Stability Guarantees for Feature Attributions","created":"2025-04-18","cited_by_count":9,"area":null},{"id":"2505.11614","title":"Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions","created":"2025-05-16","cited_by_count":9,"area":null},{"id":"2303.14496","title":"Learning with Explanation Constraints","created":"2023-03-25","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":"2410.22598","title":"Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"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":"2406.05090","title":"Provably Better Explanations with Optimized Aggregation of Feature Attributions","created":"2024-06-07","cited_by_count":6,"area":null},{"id":"2411.05841","title":"FLEXtime: Filterbank learning to explain time series","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2412.04030","title":"Mask of truth: model sensitivity to unexpected regions of medical images","created":"2024-12-05","cited_by_count":6,"area":null},{"id":"2409.14590","title":"Explainable AI needs formalization","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2602.11623","title":"TreeGrad-Ranker: Feature Ranking via $O(L)$-Time Gradients for Decision Trees","created":"2026-02-12","cited_by_count":4,"area":null},{"id":"2405.01646","title":"Explaining models relating objects and privacy","created":"2024-05-02","cited_by_count":3,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2505.11189","title":"Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2506.08928","title":"Local MDI+: Local Feature Importances for Tree-Based Models","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2310.04519","title":"SPADE: Sparsity-Guided Debugging for Deep Neural Networks","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2403.08828","title":"People Attribute Purpose to Autonomous Vehicles When Explaining Their Behavior: Insights from Cognitive Science for Explainable AI","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2410.19067","title":"Less Discriminatory Alternative and Interpretable XGBoost Framework for Binary Classification","created":"2024-10-24","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":"2605.02167","title":"Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution","created":"2026-05-04","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":"2307.06963","title":"Is Task-Agnostic Explainable AI a Myth?","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2310.04557","title":"Measuring Information in Text Explanations","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2402.11729","title":"Prospector Heads: Generalized Feature Attribution for Large Models & Data","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2404.16174","title":"MiMICRI: Towards Domain-centered Counterfactual Explanations of Cardiovascular Image Classification Models","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2405.10552","title":"Data Science Principles for Interpretable and Explainable AI","created":"2024-05-17","cited_by_count":1,"area":null},{"id":"2412.17883","title":"In Defence of Post-hoc Explainability","created":"2024-12-23","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":"2504.02016","title":"Fast Fourier Correlation is a Highly Efficient and Accurate Feature Attribution Algorithm from the Perspective of Control Theory and Game Theory","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2505.16406","title":"On the reliability of feature attribution methods for speech classification","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.24729","title":"Feature Attribution from First Principles","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.01059","title":"XAI-Units: Benchmarking Explainability Methods with Unit Tests","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2506.07229","title":"VARSHAP: Addressing Global Dependency Problems in Explainable AI with Variance-Based Local Feature Attribution","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2506.19937","title":"The Most Important Features in Generalized Additive Models Might Be Groups of Features","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2511.01932","title":"Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Models","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2602.11448","title":"Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2605.12809","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2311.06192","title":"Greedy PIG: Adaptive Integrated Gradients","created":"2023-11-10","cited_by_count":0,"area":null},{"id":"2403.03134","title":"Simplicity in Complexity : Explaining Visual Complexity using Deep Segmentation Models","created":"2024-03-05","cited_by_count":0,"area":null},{"id":"2409.06271","title":"A new paradigm for global sensitivity analysis","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2411.18343","title":"Comprehensive and Reliable Feature Attribution for Diverse Modalities and Models via Frequency-Domain Insights","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2502.12525","title":"From Abstract to Actionable: Pairwise Shapley Values for Explainable AI","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2505.06258","title":"ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability","created":"2025-05-03","cited_by_count":0,"area":null},{"id":"2508.17786","title":"Interpretable Early Failure Detection via Machine Learning and Trace Checking-based Monitoring","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2512.15783","title":"Towards AI epidemiology: a measurement standardisation framework for prospective risk detection","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2602.02239","title":"Interpretability in Deep Time Series Models Demands Semantic Alignment","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.22346","title":"First-Mover Bias in Gradient Boosting Explanations: Mechanism, Detection, and Resolution","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2605.16905","title":"AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.24727","title":"Fundamental Limitation in Explaining AI","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.29346","title":"Reliability, Faithfulness, and the Limits of Post-hoc Explanations of Opaque Scientific Models","created":"2026-06-28","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":"2607.09869","title":"Nonlinear Axiomatic Attribution for Cooperative Games","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.14271","title":"Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist","created":"2026-07-15","cited_by_count":0,"area":null}],"next_cursor":null}