{"total":199,"rows":[{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601,"area":null},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196,"area":null},{"id":"2106.12620","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","created":"2021-06-23","cited_by_count":127,"area":null},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2207.07605","title":"Algorithms to estimate Shapley value feature attributions","created":"2022-07-15","cited_by_count":115,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102,"area":null},{"id":"2205.09671","title":"A graph-transformer for whole slide image classification","created":"2022-05-19","cited_by_count":84,"area":null},{"id":"2104.00950","title":"Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey","created":"2021-04-02","cited_by_count":72,"area":null},{"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,"area":null},{"id":"2301.03505","title":"Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review","created":"2023-01-09","cited_by_count":62,"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":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2502.04320","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","created":"2025-02-06","cited_by_count":52,"area":"diffusion"},{"id":"2108.13654","title":"Discretized Integrated Gradients for Explaining Language Models","created":"2021-08-31","cited_by_count":46,"area":null},{"id":"2301.07779","title":"Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection","created":"2023-01-18","cited_by_count":44,"area":null},{"id":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2212.08158","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","created":"2022-12-15","cited_by_count":43,"area":null},{"id":"2406.04341","title":"Interpreting the Second-Order Effects of Neurons in CLIP","created":"2024-06-06","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":"2311.11108","title":"Auxiliary Losses for Learning Generalizable Concept-based Models","created":"2023-11-18","cited_by_count":35,"area":null},{"id":"2209.07924","title":"GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks","created":"2022-09-15","cited_by_count":34,"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":"2209.14279","title":"Causal Proxy Models for Concept-Based Model Explanations","created":"2022-09-28","cited_by_count":29,"area":null},{"id":"2204.04908","title":"No Token Left Behind: Explainability-Aided Image Classification and Generation","created":"2022-04-11","cited_by_count":25,"area":null},{"id":"2207.06236","title":"Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunities","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2208.11342","title":"Discovering Transferable Forensic Features for CNN-generated Images Detection","created":"2022-08-24","cited_by_count":24,"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":"2103.11257","title":"Robust Models Are More Interpretable Because Attributions Look Normal","created":"2021-03-20","cited_by_count":21,"area":null},{"id":"2311.15722","title":"GLIME: General, Stable and Local LIME Explanation","created":"2023-11-27","cited_by_count":21,"area":null},{"id":"2310.18585","title":"Visual Explanations via Iterated Integrated Attributions","created":"2023-10-28","cited_by_count":19,"area":null},{"id":"2403.14552","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","created":"2024-03-21","cited_by_count":19,"area":null},{"id":"2404.01415","title":"On the Faithfulness of Vision Transformer Explanations","created":"2024-04-01","cited_by_count":19,"area":null},{"id":"2607.05394","title":"Weak-to-Strong Generalization via Direct On-Policy Distillation","created":"2026-07-06","cited_by_count":18,"area":"distill"},{"id":"2402.04563","title":"Attention Guided CAM: Visual Explanations of Vision Transformer Guided by Self-Attention","created":"2024-02-07","cited_by_count":17,"area":null},{"id":"2408.15533","title":"LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation","created":"2024-08-28","cited_by_count":17,"area":"rag"},{"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":"2505.17495","title":"ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2105.10172","title":"Explainable Machine Learning with Prior Knowledge: An Overview","created":"2021-05-21","cited_by_count":15,"area":null},{"id":"2206.08363","title":"Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability","created":"2022-06-16","cited_by_count":15,"area":null},{"id":"2311.07621","title":"To Transformers and Beyond: Large Language Models for the Genome","created":"2023-11-13","cited_by_count":15,"area":null},{"id":"2204.06772","title":"ViTOL: Vision Transformer for Weakly Supervised Object Localization","created":"2022-04-14","cited_by_count":13,"area":null},{"id":"2106.07057","title":"FairCanary: Rapid Continuous Explainable Fairness","created":"2021-06-13","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":"2502.13870","title":"SPEX: Scaling Feature Interaction Explanations for LLMs","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2502.20134","title":"Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models","created":"2025-02-27","cited_by_count":12,"area":null},{"id":"2205.00202","title":"Explainable Artificial Intelligence for Bayesian Neural Networks: Towards trustworthy predictions of ocean dynamics","created":"2022-04-30","cited_by_count":11,"area":null},{"id":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2207.05358","title":"eX-ViT: A Novel eXplainable Vision Transformer for Weakly Supervised Semantic Segmentation","created":"2022-07-12","cited_by_count":11,"area":null},{"id":"2305.08546","title":"Towards Visual Saliency Explanations of Face Verification","created":"2023-05-15","cited_by_count":11,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2405.15495","title":"Towards Natural Machine Unlearning","created":"2024-05-24","cited_by_count":11,"area":"safety"},{"id":"2506.12766","title":"Probing Deep into Temporal Profile Makes the Infrared Small Target Detector Much Better","created":"2025-06-15","cited_by_count":11,"area":null},{"id":"2507.17657","title":"Attention (as Discrete-Time Markov) Chains","created":"2025-07-23","cited_by_count":11,"area":null},{"id":"2509.17178","title":"Attention Consistency for LLMs Explanation","created":"2025-09-21","cited_by_count":11,"area":null},{"id":"2211.02912","title":"New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2304.10755","title":"Interpretable and Robust AI in EEG Systems: A Survey","created":"2023-04-21","cited_by_count":10,"area":null},{"id":"2307.05350","title":"Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat","created":"2023-07-07","cited_by_count":10,"area":null},{"id":"2312.09783","title":"Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2401.14578","title":"GOAt: Explaining Graph Neural Networks via Graph Output Attribution","created":"2024-01-26","cited_by_count":10,"area":null},{"id":"2109.01369","title":"Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation","created":"2021-09-03","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":"2302.02023","title":"TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification","created":"2023-02-03","cited_by_count":8,"area":null},{"id":"2401.11243","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","created":"2024-01-20","cited_by_count":8,"area":null},{"id":"2107.09546","title":"Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions","created":"2021-07-20","cited_by_count":7,"area":null},{"id":"2207.11564","title":"A general-purpose method for applying Explainable AI for Anomaly Detection","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2406.05068","title":"Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations","created":"2024-06-07","cited_by_count":7,"area":null},{"id":"2407.09115","title":"Layer-Wise Relevance Propagation with Conservation Property for ResNet","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2504.07389","title":"Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression","created":"2025-04-10","cited_by_count":7,"area":null},{"id":"2112.03020","title":"Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2205.09735","title":"Foundation Posteriors for Approximate Probabilistic Inference","created":"2022-05-19","cited_by_count":6,"area":null},{"id":"2207.07465","title":"Creating an Explainable Intrusion Detection System Using Self Organizing Maps","created":"2022-07-15","cited_by_count":6,"area":null},{"id":"2207.11352","title":"Deep neural network heatmaps capture Alzheimer's disease patterns reported in a large meta-analysis of neuroimaging studies","created":"2022-07-22","cited_by_count":6,"area":null},{"id":"2304.02247","title":"Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy","created":"2023-04-05","cited_by_count":6,"area":null},{"id":"2401.03785","title":"Identifying Important Group of Pixels using Interactions","created":"2024-01-08","cited_by_count":6,"area":null},{"id":"2403.04549","title":"Explainable Face Verification via Feature-Guided Gradient Backpropagation","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2406.02443","title":"Explainable Deep Learning Analysis for Raga Identification in Indian Art Music","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2411.00132","title":"Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2507.04388","title":"Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers","created":"2025-07-06","cited_by_count":6,"area":null},{"id":"2510.07115","title":"Enhancing Concept Localization in CLIP-based Concept Bottleneck Models","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2206.03247","title":"Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2207.00812","title":"A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data","created":"2022-07-02","cited_by_count":5,"area":null},{"id":"2207.10896","title":"Privacy and Transparency in Graph Machine Learning: A Unified Perspective","created":"2022-07-22","cited_by_count":5,"area":null},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","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":"2309.11155","title":"ProtoExplorer: Interpretable Forensic Analysis of Deepfake Videos using Prototype Exploration and Refinement","created":"2023-09-20","cited_by_count":5,"area":null},{"id":"2403.14496","title":"How Human-Centered Explainable AI Interface Are Designed and Evaluated: A Systematic Survey","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2210.05883","title":"AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning","created":"2022-10-12","cited_by_count":4,"area":null},{"id":"2304.06391","title":"VISION DIFFMASK: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking","created":"2023-04-13","cited_by_count":4,"area":"mechinterp"},{"id":"2310.16584","title":"Learning to Explain: A Model-Agnostic Framework for Explaining Black Box Models","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2403.19882","title":"Enhancing Efficiency in Vision Transformer Networks: Design Techniques and Insights","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2410.23693","title":"Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation","created":"2024-10-31","cited_by_count":4,"area":"safety"},{"id":"2505.11612","title":"Heart2Mind: Human-Centered Contestable Psychiatric Disorder Diagnosis System using Wearable ECG Monitors","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2507.03197","title":"Quantifying Cross-Attention Interaction in Transformers for Interpreting TCR-pMHC Binding","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2105.06558","title":"Bias, Fairness, and Accountability with AI and ML Algorithms","created":"2021-05-13","cited_by_count":3,"area":null}],"next_cursor":"100"}