{"total":285,"rows":[{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2302.02187","title":"Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations","created":"2023-02-04","cited_by_count":83,"area":null},{"id":"2101.08758","title":"How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations","created":"2021-01-21","cited_by_count":58,"area":null},{"id":"2103.11972","title":"Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals","created":"2021-03-22","cited_by_count":55,"area":null},{"id":"2102.10936","title":"Shapley values for feature selection: The good, the bad, and the axioms","created":"2021-02-22","cited_by_count":54,"area":null},{"id":"2211.12507","title":"OpenFE: Automated Feature Generation with Expert-level Performance","created":"2022-11-22","cited_by_count":52,"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":"2205.13085","title":"Identifying Patient-Specific Root Causes with the Heteroscedastic Noise Model","created":"2022-05-25","cited_by_count":38,"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":"2107.07045","title":"Explainable AI: current status and future directions","created":"2021-07-12","cited_by_count":33,"area":null},{"id":"2205.04766","title":"Explainable Deep Learning Methods in Medical Image Classification: A Survey","created":"2022-05-10","cited_by_count":32,"area":null},{"id":"2110.09167","title":"RKHS-SHAP: Shapley Values for Kernel Methods","created":"2021-10-18","cited_by_count":30,"area":null},{"id":"2112.09745","title":"Interpretable Data-Based Explanations for Fairness Debugging","created":"2021-12-17","cited_by_count":30,"area":null},{"id":"2101.00905","title":"On Baselines for Local Feature Attributions","created":"2021-01-04","cited_by_count":29,"area":null},{"id":"2109.09847","title":"Fast TreeSHAP: Accelerating SHAP Value Computation for Trees","created":"2021-09-20","cited_by_count":29,"area":null},{"id":"2309.13775","title":"The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importance","created":"2023-09-24","cited_by_count":29,"area":null},{"id":"2410.01917","title":"Provably Accurate Shapley Value Estimation via Leverage Score Sampling","created":"2024-10-02","cited_by_count":23,"area":null},{"id":"2105.11724","title":"SHAFF: Fast and consistent SHApley eFfect estimates via random Forests","created":"2021-05-25","cited_by_count":22,"area":null},{"id":"2111.13507","title":"Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features","created":"2021-11-26","cited_by_count":19,"area":null},{"id":"2305.15167","title":"Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models","created":"2023-05-24","cited_by_count":19,"area":null},{"id":"2506.11849","title":"Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values","created":"2025-06-13","cited_by_count":19,"area":null},{"id":"2306.12330","title":"ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data","created":"2023-06-21","cited_by_count":18,"area":null},{"id":"2103.00747","title":"Combat COVID-19 Infodemic Using Explainable Natural Language Processing Models","created":"2021-03-01","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":"2112.11071","title":"Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital","created":"2021-12-21","cited_by_count":17,"area":null},{"id":"2202.07254","title":"REPID: Regional Effect Plots with implicit Interaction Detection","created":"2022-02-15","cited_by_count":17,"area":null},{"id":"2203.14196","title":"HINT: Hierarchical Neuron Concept Explainer","created":"2022-03-27","cited_by_count":17,"area":null},{"id":"2102.07048","title":"Connecting Interpretability and Robustness in Decision Trees through Separation","created":"2021-02-14","cited_by_count":16,"area":null},{"id":"2205.00359","title":"Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees","created":"2022-04-30","cited_by_count":16,"area":null},{"id":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","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":"2305.09536","title":"A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Them","created":"2023-05-16","cited_by_count":15,"area":null},{"id":"2104.11688","title":"Grouped Feature Importance and Combined Features Effect Plot","created":"2021-04-23","cited_by_count":14,"area":null},{"id":"2211.08943","title":"Comparing Explanation Methods for Traditional Machine Learning Models Part 1: An Overview of Current Methods and Quantifying Their Disagreement","created":"2022-11-16","cited_by_count":14,"area":null},{"id":"2104.04488","title":"Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks","created":"2021-04-09","cited_by_count":12,"area":null},{"id":"2111.03549","title":"Interpreting Representation Quality of DNNs for 3D Point Cloud Processing","created":"2021-11-05","cited_by_count":12,"area":null},{"id":"2202.02389","title":"The impact of feature importance methods on the interpretation of defect classifiers","created":"2022-02-04","cited_by_count":12,"area":null},{"id":"2403.04629","title":"Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration","created":"2024-03-07","cited_by_count":12,"area":null},{"id":"2104.12567","title":"Evaluating the Values of Sources in Transfer Learning","created":"2021-04-26","cited_by_count":11,"area":null},{"id":"2308.11446","title":"Exploration of the Rashomon Set Assists Trustworthy Explanations for Medical Data","created":"2023-08-22","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":"2407.19897","title":"BEExAI: Benchmark to Evaluate Explainable AI","created":"2024-07-29","cited_by_count":11,"area":null},{"id":"2102.13347","title":"MDA for random forests: inconsistency, and a practical solution via the Sobol-MDA","created":"2021-02-26","cited_by_count":10,"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":"2106.02938","title":"Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning","created":"2021-06-05","cited_by_count":10,"area":null},{"id":"2201.07849","title":"Learning-From-Disagreement: A Model Comparison and Visual Analytics Framework","created":"2022-01-19","cited_by_count":10,"area":null},{"id":"2309.11960","title":"A Comprehensive Review on Financial Explainable AI","created":"2023-09-21","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":"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":"2107.12436","title":"Feature Synergy, Redundancy, and Independence in Global Model Explanations using SHAP Vector Decomposition","created":"2021-07-26","cited_by_count":9,"area":null},{"id":"2110.03184","title":"Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2112.12635","title":"AcME -- Accelerated Model-agnostic Explanations: Fast Whitening of the Machine-Learning Black Box","created":"2021-12-23","cited_by_count":9,"area":null},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"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":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2105.09740","title":"Evaluating the Correctness of Explainable AI Algorithms for Classification","created":"2021-05-20","cited_by_count":8,"area":null},{"id":"2203.01363","title":"Faking feature importance: A cautionary tale on the use of differentially-private synthetic data","created":"2022-03-02","cited_by_count":8,"area":null},{"id":"2209.02764","title":"Change Detection for Local Explainability in Evolving Data Streams","created":"2022-09-06","cited_by_count":8,"area":null},{"id":"2305.17574","title":"Counterfactual Formulation of Patient-Specific Root Causes of Disease","created":"2023-05-27","cited_by_count":8,"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":"2309.11193","title":"RHALE: Robust and Heterogeneity-aware Accumulated Local Effects","created":"2023-09-20","cited_by_count":8,"area":null},{"id":"2601.18608","title":"PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression","created":"2026-01-26","cited_by_count":7,"area":null},{"id":"2109.05468","title":"Feature Importance in Gradient Boosting Trees with Cross-Validation Feature Selection","created":"2021-09-12","cited_by_count":6,"area":null},{"id":"2202.11919","title":"Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations","created":"2022-02-24","cited_by_count":6,"area":null},{"id":"2205.13234","title":"DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees","created":"2022-05-26","cited_by_count":6,"area":null},{"id":"2205.13662","title":"Explaining Preferences with Shapley Values","created":"2022-05-26","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":"2210.17426","title":"Trade-off Between Efficiency and Consistency for Removal-based Explanations","created":"2022-10-31","cited_by_count":6,"area":null},{"id":"2212.04805","title":"Understanding electricity prices beyond the merit order principle using explainable AI","created":"2022-12-09","cited_by_count":6,"area":null},{"id":"2302.02016","title":"Improving Interpretability via Explicit Word Interaction Graph Layer","created":"2023-02-03","cited_by_count":6,"area":null},{"id":"2302.11996","title":"K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2304.14774","title":"A feature selection method based on Shapley values robust to concept shift in regression","created":"2023-04-28","cited_by_count":6,"area":null},{"id":"2502.06152","title":"Explaining and Improving Information Complementarities in Multi-Agent Decision-making","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2504.08804","title":"Estimating Item Difficulty Using Large Language Models and Tree-Based Machine Learning Algorithms","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2104.13794","title":"Finding High-Value Training Data Subset through Differentiable Convex Programming","created":"2021-04-28","cited_by_count":5,"area":null},{"id":"2105.08589","title":"Self-interpretable Convolutional Neural Networks for Text Classification","created":"2021-05-18","cited_by_count":5,"area":null},{"id":"2112.04698","title":"Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges","created":"2021-12-09","cited_by_count":5,"area":null},{"id":"2112.10592","title":"Exact Shapley Values for Local and Model-True Explanations of Decision Tree Ensembles","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2201.07227","title":"Explainable Ensemble Machine Learning for Breast Cancer Diagnosis based on Ultrasound Image Texture Features","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2205.15750","title":"Variable importance without impossible data","created":"2022-05-31","cited_by_count":5,"area":null},{"id":"2307.04850","title":"SHAP@k:Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2310.05468","title":"Enhancing Interpretability and Generalizability in Extended Isolation Forests","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2408.16046","title":"Scaling Up Diffusion and Flow-based XGBoost Models","created":"2024-08-28","cited_by_count":5,"area":null},{"id":"2107.01988","title":"UCSL : A Machine Learning Expectation-Maximization framework for Unsupervised Clustering driven by Supervised Learning","created":"2021-07-05","cited_by_count":4,"area":null},{"id":"2108.04126","title":"Improved Feature Importance Computations for Tree Models: Shapley vs. Banzhaf","created":"2021-08-09","cited_by_count":4,"area":null},{"id":"2108.05390","title":"Seven challenges for harmonizing explainability requirements","created":"2021-08-11","cited_by_count":4,"area":null},{"id":"2204.12365","title":"Explaining Adverse Actions in Credit Decisions Using Shapley Decomposition","created":"2022-04-26","cited_by_count":4,"area":null},{"id":"2210.04995","title":"FEAMOE: Fair, Explainable and Adaptive Mixture of Experts","created":"2022-10-10","cited_by_count":4,"area":"moe"},{"id":"2301.06009","title":"Rationalizing Predictions by Adversarial Information Calibration","created":"2023-01-15","cited_by_count":4,"area":null},{"id":"2303.10931","title":"Approaching an unknown communication system by latent space exploration and causal inference","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2306.07775","title":"iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios","created":"2023-06-13","cited_by_count":4,"area":null},{"id":"2306.14911","title":"\"You might think about slightly revising the title\": identifying hedges in peer-tutoring interactions","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2308.11975","title":"Approximating Score-based Explanation Techniques Using Conformal Regression","created":"2023-08-23","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":"2312.00066","title":"Exploring Factors Affecting Pedestrian Crash Severity Using TabNet: A Deep Learning Approach","created":"2023-11-29","cited_by_count":4,"area":null},{"id":"2407.03830","title":"DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2408.03572","title":"2D-OOB: Attributing Data Contribution Through Joint Valuation Framework","created":"2024-08-07","cited_by_count":4,"area":"safety"},{"id":"2409.11992","title":"Additive-feature-attribution methods: a review on explainable artificial intelligence for fluid dynamics and heat transfer","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2410.23772","title":"Disentangling Interactions and Dependencies in Feature Attribution","created":"2024-10-31","cited_by_count":4,"area":null},{"id":"2502.15215","title":"Tensor Product Neural Networks for Functional ANOVA Model","created":"2025-02-21","cited_by_count":4,"area":null}],"next_cursor":"100"}