{"total":65,"rows":[{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91,"area":null},{"id":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88,"area":null},{"id":"2210.16156","title":"Reliability of CKA as a Similarity Measure in Deep Learning","created":"2022-10-28","cited_by_count":87,"area":null},{"id":"2503.05613","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","created":"2025-03-07","cited_by_count":76,"area":"mechinterp"},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","cited_by_count":32,"area":null},{"id":"2204.02735","title":"Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck","created":"2022-04-06","cited_by_count":30,"area":null},{"id":"2106.12447","title":"How Well do Feature Visualizations Support Causal Understanding of CNN Activations?","created":"2021-06-23","cited_by_count":28,"area":null},{"id":"2206.04394","title":"Xplique: A Deep Learning Explainability Toolbox","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2311.16681","title":"Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations","created":"2023-11-28","cited_by_count":22,"area":null},{"id":"2406.19087","title":"Dimensions underlying the representational alignment of deep neural networks with humans","created":"2024-06-27","cited_by_count":22,"area":null},{"id":"2204.02738","title":"Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network","created":"2022-04-06","cited_by_count":21,"area":null},{"id":"2203.13909","title":"Concept Embedding Analysis: A Review","created":"2022-03-25","cited_by_count":20,"area":null},{"id":"2107.13459","title":"Surrogate Model-Based Explainability Methods for Point Cloud NNs","created":"2021-07-28","cited_by_count":18,"area":null},{"id":"2303.01052","title":"Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression","created":"2023-03-02","cited_by_count":18,"area":null},{"id":"2307.16896","title":"Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training","created":"2023-07-31","cited_by_count":15,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2206.04530","title":"DORA: Exploring Outlier Representations in Deep Neural Networks","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2410.16638","title":"LLMScan: Causal Scan for LLM Misbehavior Detection","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2311.06786","title":"Explainability of Vision Transformers: A Comprehensive Review and New Perspectives","created":"2023-11-12","cited_by_count":12,"area":null},{"id":"2404.08886","title":"EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM","created":"2024-04-13","cited_by_count":12,"area":null},{"id":"2410.03595","title":"Understanding Reasoning in Chain-of-Thought from the Hopfieldian View","created":"2024-10-04","cited_by_count":11,"area":"lr"},{"id":"2307.14239","title":"Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI)","created":"2023-07-26","cited_by_count":10,"area":null},{"id":"2304.05727","title":"Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks","created":"2023-04-12","cited_by_count":9,"area":null},{"id":"2310.11431","title":"Identifying Interpretable Visual Features in Artificial and Biological Neural Systems","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2203.09505","title":"Visualizing Global Explanations of Point Cloud DNNs","created":"2022-03-17","cited_by_count":8,"area":null},{"id":"2110.04158","title":"Explainability-Aware One Point Attack for Point Cloud Neural Networks","created":"2021-10-08","cited_by_count":7,"area":null},{"id":"2106.06927","title":"Inverting Adversarially Robust Networks for Image Synthesis","created":"2021-06-13","cited_by_count":6,"area":null},{"id":"2202.09374","title":"Explaining, Evaluating and Enhancing Neural Networks' Learned Representations","created":"2022-02-18","cited_by_count":6,"area":null},{"id":"2209.13710","title":"Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledge","created":"2022-09-27","cited_by_count":6,"area":"lr"},{"id":"2308.05411","title":"Explainable AI applications in the Medical Domain: a systematic review","created":"2023-08-10","cited_by_count":5,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2205.10238","title":"Visualizing and Explaining Language Models","created":"2022-04-30","cited_by_count":4,"area":null},{"id":"2211.12173","title":"Towards Human-Interpretable Prototypes for Visual Assessment of Image Classification Models","created":"2022-11-22","cited_by_count":4,"area":null},{"id":"2305.07663","title":"Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces","created":"2023-04-30","cited_by_count":4,"area":null},{"id":"2512.02004","title":"AlignSAE: Concept-Aligned Sparse Autoencoders","created":"2025-12-01","cited_by_count":4,"area":"mechinterp"},{"id":"2206.12986","title":"Explaining the root causes of unit-level changes","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2210.06916","title":"On the Evaluation of the Plausibility and Faithfulness of Sentiment Analysis Explanations","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2303.09634","title":"Causal Temporal Graph Convolutional Neural Networks (CTGCN)","created":"2023-03-16","cited_by_count":3,"area":null},{"id":"2307.11011","title":"Neuron Sensitivity Guided Test Case Selection for Deep Learning Testing","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2311.08240","title":"Investigating the Encoding of Words in BERT's Neurons using Feature Textualization","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2401.06122","title":"Manipulating Feature Visualizations with Gradient Slingshots","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2306.00010","title":"Trainable and Explainable Simplicial Map Neural Networks","created":"2023-05-29","cited_by_count":2,"area":null},{"id":"2404.14830","title":"CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision Models","created":"2024-04-23","cited_by_count":2,"area":null},{"id":"2410.16958","title":"Leaky ReLUs That Differ in Forward and Backward Pass Facilitate Activation Maximization in Deep Neural Networks","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2504.13763","title":"Decoding Vision Transformers: the Diffusion Steering Lens","created":"2025-04-18","cited_by_count":2,"area":"mechinterp"},{"id":"2111.12795","title":"Picasso: Model-free Feature Visualization","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2112.09414","title":"Disentangled representations: towards interpretation of sex determination from hip bone","created":"2021-12-17","cited_by_count":1,"area":null},{"id":"2306.16951","title":"Applying language models to algebraic topology: generating simplicial cycles using multi-labeling in Wu's formula","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2408.01139","title":"Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2504.08602","title":"On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2508.07281","title":"Representation Understanding via Activation Maximization","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2101.01178","title":"Advances in Electron Microscopy with Deep Learning","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2107.07005","title":"WeightScale: Interpreting Weight Change in Neural Networks","created":"2021-07-07","cited_by_count":0,"area":null},{"id":"2110.09431","title":"Comparing Deep Neural Nets with UMAP Tour","created":"2021-10-18","cited_by_count":0,"area":null},{"id":"2205.08369","title":"Applications of Reinforcement Learning in Deregulated Power Market: A Comprehensive Review","created":"2022-05-07","cited_by_count":0,"area":null},{"id":"2206.09089","title":"A Dynamic Data Driven Approach for Explainable Scene Understanding","created":"2022-06-18","cited_by_count":0,"area":null},{"id":"2306.03531","title":"A Unified Concept-Based System for Local, Global, and Misclassification Explanations","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2306.13178","title":"Targeted Background Removal Creates Interpretable Feature Visualizations","created":"2023-06-22","cited_by_count":0,"area":null},{"id":"2404.02830","title":"Enhancing Interpretability of Vertebrae Fracture Grading using Human-interpretable Prototypes","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2506.17040","title":"Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual Invariance","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2507.10106","title":"BlueGlass: A Framework for Composite AI Safety","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2606.25606","title":"Expresso-AI: Explainable Video-Based Deep Learning Models for Depression Diagnosis","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.05399","title":"From Interpretability Methods to Interpretable Models","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}