{"list":"other","total":111,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"1910.01279","title":"Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks","created":"2019-10-03","cited_by_count":582},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"2012.15445","title":"Explainability in Graph Neural Networks: A Taxonomic Survey","created":"2020-12-31","cited_by_count":384},{"id":"1908.08474","title":"The many Shapley values for model explanation","created":"2019-08-22","cited_by_count":344},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"1901.09392","title":"On the (In)fidelity and Sensitivity for Explanations","created":"2019-01-27","cited_by_count":310},{"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},{"id":"2012.14261","title":"A Survey on Neural Network Interpretability","created":"2020-12-28","cited_by_count":291},{"id":"2011.11108","title":"Multiresolution Knowledge Distillation for Anomaly Detection","created":"2020-11-22","cited_by_count":285},{"id":"1910.08485","title":"Understanding Deep Networks via Extremal Perturbations and Smooth Masks","created":"2019-10-18","cited_by_count":259},{"id":"1512.02479","title":"Explaining NonLinear Classification Decisions with Deep Taylor Decomposition","created":"2015-12-08","cited_by_count":250},{"id":"1705.07857","title":"Real Time Image Saliency for Black Box Classifiers","created":"2017-05-22","cited_by_count":246},{"id":"1808.00033","title":"Techniques for Interpretable Machine Learning","created":"2018-07-31","cited_by_count":238},{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236},{"id":"2011.14878","title":"Explaining by Removing: A Unified Framework for Model Explanation","created":"2020-11-21","cited_by_count":218},{"id":"1906.07983","title":"Explanations can be manipulated and geometry is to blame","created":"2019-06-19","cited_by_count":216},{"id":"2002.11097","title":"Problems with Shapley-value-based explanations as feature importance measures","created":"2020-02-25","cited_by_count":200},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"1802.00614","title":"Visual Interpretability for Deep Learning: a Survey","created":"2018-02-02","cited_by_count":155},{"id":"1909.13584","title":"Interpretations are useful: penalizing explanations to align neural networks with prior knowledge","created":"2019-09-30","cited_by_count":145},{"id":"1902.05622","title":"The Shapley Taylor Interaction Index","created":"2019-02-14","cited_by_count":143},{"id":"2403.03431","title":"Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing","created":"2024-03-06","cited_by_count":135},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128},{"id":"2004.11207","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","created":"2020-04-23","cited_by_count":125},{"id":"1912.01451","title":"Sanity Checks for Saliency Metrics","created":"2019-11-29","cited_by_count":119},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118},{"id":"1902.02041","title":"Fooling Neural Network Interpretations via Adversarial Model Manipulation","created":"2019-02-06","cited_by_count":112},{"id":"2001.00396","title":"Restricting the Flow: Information Bottlenecks for Attribution","created":"2020-01-02","cited_by_count":110},{"id":"2011.01625","title":"Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models","created":"2020-11-03","cited_by_count":107},{"id":"2002.04138","title":"Explaining Explanations: Axiomatic Feature Interactions for Deep Networks","created":"2020-02-10","cited_by_count":103},{"id":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102},{"id":"1910.12336","title":"CXPlain: Causal Explanations for Model Interpretation under Uncertainty","created":"2019-10-27","cited_by_count":98},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98},{"id":"1912.09818","title":"When Explanations Lie: Why Many Modified BP Attributions Fail","created":"2019-12-20","cited_by_count":92},{"id":"1907.09701","title":"Benchmarking Attribution Methods with Relative Feature Importance","created":"2019-07-23","cited_by_count":89},{"id":"2001.03447","title":"Explaining the Explainer: A First Theoretical Analysis of LIME","created":"2020-01-10","cited_by_count":89},{"id":"1705.05598","title":"Learning how to explain neural networks: PatternNet and PatternAttribution","created":"2017-05-16","cited_by_count":84},{"id":"1902.02302","title":"Neural Network Attributions: A Causal Perspective","created":"2019-02-06","cited_by_count":77},{"id":"2007.09969","title":"Fairwashing Explanations with Off-Manifold Detergent","created":"2020-07-20","cited_by_count":72},{"id":"2305.06311","title":"Automatic Evaluation of Attribution by Large Language Models","created":"2023-05-10","cited_by_count":72},{"id":"2311.03731","title":"A Survey of Large Language Models Attribution","created":"2023-11-07","cited_by_count":71},{"id":"2203.00870","title":"Faith-Shap: The Faithful Shapley Interaction Index","created":"2022-03-02","cited_by_count":69},{"id":"2202.11912","title":"A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions","created":"2022-02-24","cited_by_count":64},{"id":"1805.07039","title":"A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations","created":"2018-05-18","cited_by_count":60},{"id":"2010.12016","title":"Towards falsifiable interpretability research","created":"2020-10-22","cited_by_count":53},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52},{"id":"2106.07875","title":"S-LIME: Stabilized-LIME for Model Explanation","created":"2021-06-15","cited_by_count":52},{"id":"2012.03058","title":"BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations","created":"2020-12-05","cited_by_count":51},{"id":"1908.02686","title":"Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks","created":"2019-08-07","cited_by_count":49},{"id":"2102.10618","title":"Towards the Unification and Robustness of Perturbation and Gradient Based Explanations","created":"2021-02-21","cited_by_count":47},{"id":"2103.14651","title":"Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice","created":"2021-03-27","cited_by_count":45},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45},{"id":"2012.10425","title":"Towards Robust Explanations for Deep Neural Networks","created":"2020-12-18","cited_by_count":43},{"id":"2204.05514","title":"A Comparative Study of Faithfulness Metrics for Model Interpretability Methods","created":"2022-04-12","cited_by_count":39},{"id":"2006.06643","title":"Smoothed Geometry for Robust Attribution","created":"2020-06-11","cited_by_count":38},{"id":"2105.00108","title":"Explaining a Series of Models by Propagating Shapley Values","created":"2021-04-30","cited_by_count":37},{"id":"2111.06206","title":"Defining and Quantifying the Emergence of Sparse Concepts in DNNs","created":"2021-11-11","cited_by_count":36},{"id":"2209.13429","title":"WeightedSHAP: analyzing and improving Shapley based feature attributions","created":"2022-09-27","cited_by_count":36},{"id":"1902.04893","title":"Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps","created":"2019-02-13","cited_by_count":34},{"id":"2204.11028","title":"Reinforced Causal Explainer for Graph Neural Networks","created":"2022-04-23","cited_by_count":34},{"id":"1906.10670","title":"Improving performance of deep learning models with axiomatic attribution priors and expected gradients","created":"2019-06-25","cited_by_count":32},{"id":"1804.00506","title":"Towards Explanation of DNN-based Prediction with Guided Feature Inversion","created":"2018-03-19","cited_by_count":31},{"id":"2006.05714","title":"OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms","created":"2020-06-10","cited_by_count":30},{"id":"2303.13731","title":"How Does Attention Work in Vision Transformers? A Visual Analytics Attempt","created":"2023-03-24","cited_by_count":30},{"id":"1907.06831","title":"Evaluating Explanation Without Ground Truth in Interpretable Machine Learning","created":"2019-07-16","cited_by_count":29},{"id":"2205.10435","title":"Towards Better Understanding Attribution Methods","created":"2022-05-20","cited_by_count":28},{"id":"2010.12487","title":"An Analysis of LIME for Text Data","created":"2020-10-23","cited_by_count":25},{"id":"2211.05667","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","created":"2022-11-10","cited_by_count":22},{"id":"2102.06307","title":"What does LIME really see in images?","created":"2021-02-11","cited_by_count":21},{"id":"2311.15722","title":"GLIME: General, Stable and Local LIME Explanation","created":"2023-11-27","cited_by_count":21},{"id":"2008.05895","title":"Can We Trust Your Explanations? Sanity Checks for Interpreters in Android Malware Analysis","created":"2020-08-13","cited_by_count":20},{"id":"2008.11092","title":"Looking Deeper into Tabular LIME","created":"2020-08-25","cited_by_count":20},{"id":"2202.12270","title":"Evaluating Feature Attribution Methods in the Image Domain","created":"2022-02-22","cited_by_count":19},{"id":"2306.07462","title":"On the Robustness of Removal-Based Feature Attributions","created":"2023-06-12","cited_by_count":19},{"id":"2106.10191","title":"Rational Shapley Values","created":"2021-06-18","cited_by_count":18},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18},{"id":"2111.03536","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-11-05","cited_by_count":17},{"id":"2309.09901","title":"The role of causality in explainable artificial intelligence","created":"2023-09-18","cited_by_count":17},{"id":"2406.15156","title":"Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs","created":"2024-06-21","cited_by_count":16}],"next_cursor":"100"}