{"total":69,"rows":[{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"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":"2410.01649","title":"shapiq: Shapley Interactions for Machine Learning","created":"2024-10-02","cited_by_count":43,"area":null},{"id":"2401.12069","title":"Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles","created":"2024-01-22","cited_by_count":31,"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":"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":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"area":null},{"id":"2104.04515","title":"Connecting Attributions and QA Model Behavior on Realistic Counterfactuals","created":"2021-04-09","cited_by_count":20,"area":null},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2102.13519","title":"PredDiff: Explanations and Interactions from Conditional Expectations","created":"2021-02-26","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":"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":"2302.03225","title":"Efficient XAI Techniques: A Taxonomic Survey","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2104.12437","title":"Towards Rigorous Interpretations: a Formalisation of Feature Attribution","created":"2021-04-26","cited_by_count":11,"area":null},{"id":"2108.13961","title":"Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools","created":"2021-08-31","cited_by_count":11,"area":null},{"id":"2408.08137","title":"Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability","created":"2024-08-15","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":"2405.06604","title":"Explaining Text Similarity in Transformer Models","created":"2024-05-10","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":"2601.18608","title":"PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression","created":"2026-01-26","cited_by_count":7,"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":"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":"2405.13474","title":"Why do explanations fail? A typology and discussion on failures in XAI","created":"2024-05-22","cited_by_count":6,"area":null},{"id":"2405.20404","title":"JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution","created":"2024-05-30","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":"2104.09073","title":"Improving Attribution Methods by Learning Submodular Functions","created":"2021-04-19","cited_by_count":5,"area":null},{"id":"2209.03798","title":"ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques","created":"2022-09-08","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":"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":"2409.13684","title":"The FIX Benchmark: Extracting Features Interpretable to eXperts","created":"2024-09-20","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":"2210.02719","title":"Continuous Diagnosis and Prognosis by Controlling the Update Process of Deep Neural Networks","created":"2022-10-06","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":"2111.05898","title":"Beyond Importance Scores: Interpreting Tabular ML by Visualizing Feature Semantics","created":"2021-11-10","cited_by_count":3,"area":null},{"id":"2204.03225","title":"Explicit Feature Interaction-aware Graph Neural Networks","created":"2022-04-07","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":"2209.10082","title":"Generalized Groves of Neural Additive Models: Pursuing transparent and accurate machine learning models in finance","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2209.10127","title":"Interpretable Selective Learning in Credit Risk","created":"2022-09-21","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":"2305.06862","title":"A General Framework for Visualizing Embedding Spaces of Neural Survival Analysis Models Based on Angular Information","created":"2023-05-11","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":"2508.18715","title":"EMMM, Explain Me My Model! Explainable Machine Generated Text Detection in Dialogues","created":"2025-08-26","cited_by_count":2,"area":null},{"id":"2511.03831","title":"Higher-Order Causal Structure Learning with Additive Models","created":"2025-11-05","cited_by_count":2,"area":null},{"id":"2212.13014","title":"Bias Mitigation Framework for Intersectional Subgroups in Neural Networks","created":"2022-12-26","cited_by_count":1,"area":null},{"id":"2305.07224","title":"Asymmetric feature interaction for interpreting model predictions","created":"2023-05-12","cited_by_count":1,"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":"2408.00251","title":"Discovering Car-following Dynamics from Trajectory Data through Deep Learning","created":"2024-08-01","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":"2207.14160","title":"Do We Need Another Explainable AI Method? Toward Unifying Post-hoc XAI Evaluation Methods into an Interactive and Multi-dimensional Benchmark","created":"2022-06-08","cited_by_count":0,"area":null},{"id":"2308.13797","title":"DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Series","created":"2023-08-26","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":"2312.08157","title":"CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problem","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2403.16554","title":"PE: A Poincare Explanation Method for Fast Text Hierarchy Generation","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2405.11476","title":"NubbleDrop: A Simple Way to Improve Matching Strategy for Prompted One-Shot Segmentation","created":"2024-05-19","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":"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":"2606.10877","title":"XtrAIn: Training-Guided Occlusion for Feature Attribution","created":"2026-06-09","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}