{"total":333,"rows":[{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"area":null},{"id":"2202.06861","title":"Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond","created":"2022-02-14","cited_by_count":171,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"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":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2301.03028","title":"Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement","created":"2023-01-08","cited_by_count":90,"area":null},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2106.05303","title":"Explaining Time Series Predictions with Dynamic Masks","created":"2021-06-09","cited_by_count":73,"area":null},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68,"area":null},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"area":null},{"id":"2209.09056","title":"Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off","created":"2022-09-19","cited_by_count":61,"area":null},{"id":"2206.01794","title":"Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology","created":"2022-06-03","cited_by_count":58,"area":null},{"id":"2209.11222","title":"Concept Activation Regions: A Generalized Framework For Concept-Based Explanations","created":"2022-09-22","cited_by_count":57,"area":null},{"id":"2304.14068","title":"Interpretable Neural-Symbolic Concept Reasoning","created":"2023-04-27","cited_by_count":57,"area":null},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2106.06804","title":"Entropy-based Logic Explanations of Neural Networks","created":"2021-06-12","cited_by_count":51,"area":null},{"id":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48,"area":null},{"id":"2211.00541","title":"Logic-Based Explainability in Machine Learning","created":"2022-10-24","cited_by_count":48,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2207.09615","title":"Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability","created":"2022-07-20","cited_by_count":46,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2111.00358","title":"A Survey on the Robustness of Feature Importance and Counterfactual Explanations","created":"2021-10-30","cited_by_count":39,"area":null},{"id":"2107.00323","title":"Combining Feature and Instance Attribution to Detect Artifacts","created":"2021-07-01","cited_by_count":38,"area":null},{"id":"2202.07728","title":"Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis","created":"2022-02-15","cited_by_count":38,"area":null},{"id":"2204.08945","title":"Missingness Bias in Model Debugging","created":"2022-04-19","cited_by_count":38,"area":null},{"id":"2206.07438","title":"Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview","created":"2022-06-15","cited_by_count":37,"area":null},{"id":"2312.12141","title":"Neuron-Level Knowledge Attribution in Large Language Models","created":"2023-12-19","cited_by_count":37,"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":"2105.08621","title":"Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks","created":"2021-05-18","cited_by_count":35,"area":null},{"id":"2107.11889","title":"GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks","created":"2021-07-25","cited_by_count":35,"area":null},{"id":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2410.01971","title":"Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust","created":"2024-10-02","cited_by_count":33,"area":"vla"},{"id":"2311.03533","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models","created":"2023-11-06","cited_by_count":32,"area":null},{"id":"2110.08412","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","created":"2021-10-15","cited_by_count":31,"area":null},{"id":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","cited_by_count":31,"area":null},{"id":"2104.08782","title":"On the Sensitivity and Stability of Model Interpretations in NLP","created":"2021-04-18","cited_by_count":30,"area":null},{"id":"2104.11914","title":"EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case","created":"2021-04-24","cited_by_count":30,"area":null},{"id":"2107.09234","title":"Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior","created":"2021-07-20","cited_by_count":29,"area":null},{"id":"2106.10185","title":"NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights","created":"2021-06-18","cited_by_count":28,"area":null},{"id":"2106.10649","title":"CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency","created":"2021-06-20","cited_by_count":28,"area":null},{"id":"2202.03407","title":"Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience","created":"2022-02-07","cited_by_count":28,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2208.09418","title":"SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability","created":"2022-08-19","cited_by_count":28,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2201.11569","title":"Human Interpretation of Saliency-based Explanation Over Text","created":"2022-01-27","cited_by_count":25,"area":null},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25,"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":"2112.08440","title":"Climate-Invariant Machine Learning","created":"2021-12-14","cited_by_count":24,"area":null},{"id":"2209.06528","title":"Explainable AI for clinical and remote health applications: a survey on tabular and time series data","created":"2022-09-14","cited_by_count":24,"area":null},{"id":"2106.08641","title":"Best of both worlds: local and global explanations with human-understandable concepts","created":"2021-06-16","cited_by_count":22,"area":null},{"id":"2211.05667","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2211.12486","title":"Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2211.16080","title":"Understanding and Enhancing Robustness of Concept-based Models","created":"2022-11-29","cited_by_count":22,"area":null},{"id":"2306.04292","title":"Dear XAI Community, We Need to Talk! Fundamental Misconceptions in Current XAI Research","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2404.02233","title":"Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models","created":"2024-04-02","cited_by_count":22,"area":null},{"id":"2101.00196","title":"On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification","created":"2021-01-01","cited_by_count":21,"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":"2111.04927","title":"Self-Interpretable Model with TransformationEquivariant Interpretation","created":"2021-11-09","cited_by_count":21,"area":null},{"id":"2205.15834","title":"Attribution-based Explanations that Provide Recourse Cannot be Robust","created":"2022-05-31","cited_by_count":20,"area":null},{"id":"2406.01583","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2306.07462","title":"On the Robustness of Removal-Based Feature Attributions","created":"2023-06-12","cited_by_count":19,"area":null},{"id":"2103.10005","title":"Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset","created":"2021-03-18","cited_by_count":18,"area":null},{"id":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2110.00527","title":"Consistent Explanations by Contrastive Learning","created":"2021-10-01","cited_by_count":18,"area":null},{"id":"2207.13586","title":"Encoding Concepts in Graph Neural Networks","created":"2022-07-27","cited_by_count":18,"area":null},{"id":"2212.05990","title":"On Computing Probabilistic Abductive Explanations","created":"2022-12-12","cited_by_count":18,"area":null},{"id":"2402.02872","title":"How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning","created":"2024-02-05","cited_by_count":18,"area":null},{"id":"2203.14196","title":"HINT: Hierarchical Neuron Concept Explainer","created":"2022-03-27","cited_by_count":17,"area":null},{"id":"2301.02437","title":"Valid P-Value for Deep Learning-Driven Salient Region","created":"2023-01-06","cited_by_count":17,"area":null},{"id":"2407.15527","title":"Interpretable Concept-Based Memory Reasoning","created":"2024-07-22","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":"2105.12837","title":"Fooling Partial Dependence via Data Poisoning","created":"2021-05-26","cited_by_count":16,"area":"safety"},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2211.14736","title":"Attribution-based XAI Methods in Computer Vision: A Review","created":"2022-11-27","cited_by_count":16,"area":null},{"id":"2404.19456","title":"A Survey of Imitation Learning Methods, Environments and Metrics","created":"2024-04-30","cited_by_count":16,"area":"offlinerl"},{"id":"2409.16756","title":"Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics","created":"2024-09-25","cited_by_count":16,"area":null},{"id":"2105.06506","title":"Sanity Simulations for Saliency Methods","created":"2021-05-13","cited_by_count":15,"area":null},{"id":"2112.06924","title":"Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing","created":"2021-12-13","cited_by_count":15,"area":null},{"id":"2201.10528","title":"Explainability in Music Recommender Systems","created":"2022-01-25","cited_by_count":15,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"area":null},{"id":"2204.12406","title":"A survey on attention mechanisms for medical applications: are we moving towards better algorithms?","created":"2022-04-26","cited_by_count":15,"area":null},{"id":"2212.06925","title":"On the Relationship Between Explanation and Prediction: A Causal View","created":"2022-12-13","cited_by_count":14,"area":null},{"id":"2304.06715","title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","created":"2023-04-13","cited_by_count":14,"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":"2412.15249","title":"LitLLMs, LLMs for Literature Review: Are we there yet?","created":"2024-12-15","cited_by_count":14,"area":null},{"id":"1802.02195","title":"Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks","created":"2018-02-06","cited_by_count":13,"area":"moe"},{"id":"2108.05312","title":"Towards Interpretable Deep Networks for Monocular Depth Estimation","created":"2021-08-11","cited_by_count":12,"area":null},{"id":"2208.12485","title":"Concept-Based Techniques for \"Musicologist-friendly\" Explanations in a Deep Music Classifier","created":"2022-08-26","cited_by_count":12,"area":null},{"id":"2311.17983","title":"Improving Interpretation Faithfulness for Vision Transformers","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2402.00794","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2411.09973","title":"Establishing and Evaluating Trustworthy AI: Overview and Research Challenges","created":"2024-11-15","cited_by_count":12,"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":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2302.12893","title":"Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluation","created":"2023-02-24","cited_by_count":11,"area":null}],"next_cursor":"100"}