{"total":95,"rows":[{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91,"area":null},{"id":"2203.00870","title":"Faith-Shap: The Faithful Shapley Interaction Index","created":"2022-03-02","cited_by_count":69,"area":null},{"id":"2303.01179","title":"SHAP-IQ: Unified Approximation of any-order Shapley Interactions","created":"2023-03-02","cited_by_count":51,"area":null},{"id":"2111.06236","title":"Discovering and Explaining the Representation Bottleneck of DNNs","created":"2021-11-11","cited_by_count":42,"area":null},{"id":"2209.11799","title":"Augmenting Interpretable Models with LLMs during Training","created":"2022-09-23","cited_by_count":38,"area":null},{"id":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2111.06206","title":"Defining and Quantifying the Emergence of Sparse Concepts in DNNs","created":"2021-11-11","cited_by_count":36,"area":null},{"id":"2403.10415","title":"Gradient based Feature Attribution in Explainable AI: A Technical Review","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2209.09326","title":"Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection","created":"2022-09-19","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":"2302.13080","title":"Does a Neural Network Really Encode Symbolic Concepts?","created":"2023-02-25","cited_by_count":27,"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":"2405.10852","title":"KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactions","created":"2024-05-17","cited_by_count":22,"area":null},{"id":"2110.00603","title":"Algorithm Fairness in AI for Medicine and Healthcare","created":"2021-10-01","cited_by_count":21,"area":null},{"id":"2203.13909","title":"Concept Embedding Analysis: A Review","created":"2022-03-25","cited_by_count":20,"area":null},{"id":"2102.13519","title":"PredDiff: Explanations and Interactions from Conditional Expectations","created":"2021-02-26","cited_by_count":17,"area":null},{"id":"2111.03536","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-11-05","cited_by_count":17,"area":null},{"id":"2102.06761","title":"MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Dataset","created":"2021-02-12","cited_by_count":15,"area":null},{"id":"2304.07670","title":"Explanations of Black-Box Models based on Directional Feature Interactions","created":"2023-04-16","cited_by_count":15,"area":null},{"id":"2108.06895","title":"Interpreting Attributions and Interactions of Adversarial Attacks","created":"2021-08-16","cited_by_count":13,"area":null},{"id":"2207.11694","title":"Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability","created":"2022-07-24","cited_by_count":12,"area":null},{"id":"2502.14862","title":"Interpretable Text Embeddings and Text Similarity Explanation: A Survey","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2305.17073","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2105.10719","title":"Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?","created":"2021-05-22","cited_by_count":10,"area":null},{"id":"2401.17441","title":"Explaining Predictive Uncertainty by Exposing Second-Order Effects","created":"2024-01-30","cited_by_count":10,"area":null},{"id":"2412.17152","title":"Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory","created":"2024-12-22","cited_by_count":10,"area":null},{"id":"2302.13095","title":"Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts","created":"2023-02-25","cited_by_count":9,"area":null},{"id":"2405.06604","title":"Explaining Text Similarity in Transformer Models","created":"2024-05-10","cited_by_count":9,"area":null},{"id":"2405.20805","title":"Multilingual Text Style Transfer: Datasets & Models for Indian Languages","created":"2024-05-31","cited_by_count":9,"area":null},{"id":"2306.12181","title":"Feature Interactions Reveal Linguistic Structure in Language Models","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2408.17198","title":"Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features","created":"2024-08-30","cited_by_count":7,"area":null},{"id":"2103.00370","title":"Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning","created":"2021-02-28","cited_by_count":6,"area":null},{"id":"2210.17426","title":"Trade-off Between Efficiency and Consistency for Removal-based Explanations","created":"2022-10-31","cited_by_count":6,"area":null},{"id":"2401.06462","title":"AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Finding","created":"2024-01-12","cited_by_count":6,"area":null},{"id":"2103.03103","title":"Interpretable Artificial Intelligence through the Lens of Feature Interaction","created":"2021-03-01","cited_by_count":5,"area":null},{"id":"2305.10181","title":"Exploring the cloud of feature interaction scores in a Rashomon set","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2306.13753","title":"Four Axiomatic Characterizations of the Integrated Gradients Attribution Method","created":"2023-06-23","cited_by_count":5,"area":null},{"id":"2311.00858","title":"SmoothHess: ReLU Network Feature Interactions via Stein's Lemma","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2406.15085","title":"Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2505.17630","title":"Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2105.08039","title":"Fine-grained Interpretation and Causation Analysis in Deep NLP Models","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2111.13786","title":"Learning from learning machines: a new generation of AI technology to meet the needs of science","created":"2021-11-27","cited_by_count":4,"area":null},{"id":"2305.00799","title":"How to address monotonicity for model risk management?","created":"2023-04-28","cited_by_count":4,"area":null},{"id":"2402.17516","title":"QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanations","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2111.05898","title":"Beyond Importance Scores: Interpreting Tabular ML by Visualizing Feature Semantics","created":"2021-11-10","cited_by_count":3,"area":null},{"id":"2208.06096","title":"Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insights","created":"2022-08-12","cited_by_count":3,"area":null},{"id":"2210.14195","title":"Using Deep Learning to Find the Next Unicorn: A Practical Synthesis","created":"2022-10-18","cited_by_count":3,"area":null},{"id":"2305.09400","title":"Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification","created":"2023-05-16","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":"2502.06661","title":"iLOCO: Distribution-Free Inference for Feature Interactions","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2203.09073","title":"Ask to Understand: Question Generation for Multi-hop Question Answering","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2305.03100","title":"Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainability","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2311.12418","title":"Visual Analytics for Generative Transformer Models","created":"2023-11-21","cited_by_count":2,"area":null},{"id":"2411.15265","title":"Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI","created":"2024-11-22","cited_by_count":2,"area":null},{"id":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2511.05064","title":"Order-Level Attention Similarity Across Language Models: A Latent Commonality","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2606.00557","title":"Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures","created":"2026-05-30","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":"2305.09204","title":"The Weighted M\\\"obius Score: A Unified Framework for Feature Attribution","created":"2023-05-16","cited_by_count":1,"area":null},{"id":"2309.13411","title":"Towards Attributions of Input Variables in a Coalition","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2309.15319","title":"DeepROCK: Error-controlled interaction detection in deep neural networks","created":"2023-09-26","cited_by_count":1,"area":null},{"id":"2310.13506","title":"Explaining Interactions Between Text Spans","created":"2023-10-20","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":"2406.03594","title":"Why is \"Problems\" Predictive of Positive Sentiment? A Case Study of Explaining Unintuitive Features in Sentiment Classification","created":"2024-06-05","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":"2510.06165","title":"Higher-Order Feature Attribution: Bridging Statistics, Explainable AI, and Topological Signal Processing","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2602.16608","title":"Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.22045","title":"H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.19410","title":"The Representational Limit of Scalar Interactions: An Interventional Decomposition","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2607.20848","title":"Auditing Evidence Use in Medical LLM Diagnosis","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2103.02405","title":"Relate and Predict: Structure-Aware Prediction with Jointly Optimized Neural DAG","created":"2021-03-03","cited_by_count":0,"area":null},{"id":"2103.07364","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-03-12","cited_by_count":0,"area":null},{"id":"2212.12374","title":"Relational Local Explanations","created":"2022-12-23","cited_by_count":0,"area":null},{"id":"2307.00758","title":"Structured Network Pruning by Measuring Filter-wise Interactions","created":"2023-07-03","cited_by_count":0,"area":null},{"id":"2309.01780","title":"Measuring, Interpreting, and Improving Fairness of Algorithms using Causal Inference and Randomized Experiments","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2309.08999","title":"Context-aware Adversarial Attack on Named Entity Recognition","created":"2023-09-16","cited_by_count":0,"area":null},{"id":"2310.09780","title":"Notes on Applicability of Explainable AI Methods to Machine Learning Models Using Features Extracted by Persistent Homology","created":"2023-10-15","cited_by_count":0,"area":null},{"id":"2402.06295","title":"Multimodal Interpretable Data-Driven Models for Early Prediction of Antimicrobial Multidrug Resistance Using Multivariate Time-Series","created":"2024-02-09","cited_by_count":0,"area":null},{"id":"2408.17016","title":"Error-controlled non-additive interaction discovery in machine learning models","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2507.11855","title":"OrdShap: Feature Position Importance for Sequential Black-Box Models","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2509.10825","title":"CUBE: Contrastive Understanding by Balanced Experiments","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2510.27207","title":"Feature-Function Curvature Analysis: A Geometric Framework for Explaining Differentiable Models","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2511.13658","title":"Why is \"Chicago\" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2603.02906","title":"Towards Accurate and Interpretable Time-series Forecasting: A Polynomial Learning Approach","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.28597","title":"Position: Explainable AI is Causality in Disguise","created":"2026-03-30","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":"2606.06224","title":"Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.07204","title":"Restricted Dynamic Geometric Complexity: Path-Space Reduction and M\\\"obius--Jacobi Response","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.07206","title":"Causal Optimizer Interaction Calculus: Hidden Geometric Relaxation and Identifiable Interventions","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.14096","title":"IMEX Interaction-Based Model Explanation","created":"2026-04-16","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},{"id":"2607.20201","title":"The Quadrilateral Loss: Additivity as a Measurable Behavior of Dense Neural Networks","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.06486","title":"Beyond Attention: Signed Integrated Gradients Attribution in a BiomeGPT-Style Microbiome Transformer","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.25315","title":"Activation-Space Order-Swap Geometry: A Site-Asymmetry Audit","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}