{"total":120,"rows":[{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243,"area":null},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"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":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91,"area":"mechinterp"},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2305.06386","title":"Text-To-Concept (and Back) via Cross-Model Alignment","created":"2023-05-10","cited_by_count":64,"area":null},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","cited_by_count":50,"area":null},{"id":"2406.08074","title":"A Concept-Based Explainability Framework for Large Multimodal Models","created":"2024-06-12","cited_by_count":39,"area":"mllm"},{"id":"2306.00966","title":"The Hidden Language of Diffusion Models","created":"2023-06-01","cited_by_count":34,"area":"diffusion"},{"id":"2307.10504","title":"Identifying Interpretable Subspaces in Image Representations","created":"2023-07-20","cited_by_count":32,"area":null},{"id":"2202.03482","title":"Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence","created":"2022-02-07","cited_by_count":25,"area":null},{"id":"2205.14108","title":"Scalable Interpretability via Polynomials","created":"2022-05-27","cited_by_count":25,"area":null},{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","cited_by_count":25,"area":null},{"id":"2401.10831","title":"Understanding Video Transformers via Universal Concept Discovery","created":"2024-01-19","cited_by_count":23,"area":"mechinterp"},{"id":"2309.07742","title":"Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning","created":"2023-09-14","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":"2203.13909","title":"Concept Embedding Analysis: A Review","created":"2022-03-25","cited_by_count":20,"area":null},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2407.03921","title":"Concept Bottleneck Models Without Predefined Concepts","created":"2024-07-04","cited_by_count":17,"area":null},{"id":"2305.06754","title":"COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks","created":"2023-05-11","cited_by_count":16,"area":null},{"id":"2412.11576","title":"DCBM: Data-Efficient Visual Concept Bottleneck Models","created":"2024-12-16","cited_by_count":16,"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":"2204.11642","title":"Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset","created":"2022-04-25","cited_by_count":13,"area":null},{"id":"2309.03234","title":"Natural Example-Based Explainability: a Survey","created":"2023-09-05","cited_by_count":13,"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":"2212.08733","title":"Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ","created":"2022-12-16","cited_by_count":12,"area":null},{"id":"2411.05698","title":"Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification","created":"2024-11-08","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":"2304.14864","title":"Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability","created":"2023-04-28","cited_by_count":11,"area":null},{"id":"2412.06639","title":"Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers","created":"2024-12-09","cited_by_count":11,"area":null},{"id":"2311.15303","title":"Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement","created":"2023-11-26","cited_by_count":10,"area":null},{"id":"2404.18533","title":"Evaluating Readability and Faithfulness of Concept-based Explanations","created":"2024-04-29","cited_by_count":10,"area":null},{"id":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2510.11675","title":"FACE: Faithful Automatic Concept Extraction","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2403.14566","title":"A survey on Concept-based Approaches For Model Improvement","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2404.10356","title":"Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery","created":"2024-04-16","cited_by_count":8,"area":"diffusion"},{"id":"2311.14435","title":"Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces","created":"2023-11-24","cited_by_count":7,"area":null},{"id":"2404.13567","title":"On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis","created":"2024-04-21","cited_by_count":6,"area":null},{"id":"2406.12649","title":"Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2506.13831","title":"Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2303.09171","title":"Empowering CAM-Based Methods with Capability to Generate Fine-Grained and High-Faithfulness Explanations","created":"2023-03-16","cited_by_count":5,"area":null},{"id":"2503.15699","title":"Representational Similarity via Interpretable Visual Concepts","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2505.17883","title":"FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2601.05328","title":"Bi-Orthogonal Factor Decomposition for Vision Transformers","created":"2026-01-08","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":"2203.06043","title":"Sparse Subspace Clustering for Concept Discovery (SSCCD)","created":"2022-03-11","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":"2406.01649","title":"CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanations","created":"2024-06-03","cited_by_count":4,"area":"diffusion"},{"id":"2503.18629","title":"Towards Human-Understandable Multi-Dimensional Concept Discovery","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2506.05774","title":"Evaluating Neuron Explanations: A Unified Framework with Sanity Checks","created":"2025-06-06","cited_by_count":4,"area":"mechinterp"},{"id":"2603.07343","title":"Learning Concept Bottleneck Models from Mechanistic Explanations","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2211.08425","title":"A Rigorous Study Of The Deep Taylor Decomposition","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2306.08933","title":"Towards Interpretability in Audio and Visual Affective Machine Learning: A Review","created":"2023-06-15","cited_by_count":3,"area":null},{"id":"2402.01292","title":"From Evidence to Decision: Exploring Evaluative AI","created":"2024-02-02","cited_by_count":3,"area":null},{"id":"2410.17832","title":"Exploiting Text-Image Latent Spaces for the Description of Visual Concepts","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2502.16105","title":"NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2509.24058","title":"On The Variability of Concept Activation Vectors","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2602.23947","title":"Hierarchical Concept-based Interpretable Models","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2211.10807","title":"Concept-based Explanations using Non-negative Concept Activation Vectors and Decision Tree for CNN Models","created":"2022-11-19","cited_by_count":2,"area":null},{"id":"2308.12053","title":"Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2309.00018","title":"Unsupervised discovery of Interpretable Visual Concepts","created":"2023-08-31","cited_by_count":2,"area":null},{"id":"2404.07008","title":"Knowledge graphs for empirical concept retrieval","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2404.16532","title":"Global Concept Explanations for Graphs by Contrastive Learning","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2405.02583","title":"Explainable Interface for Human-Autonomy Teaming: A Survey","created":"2024-05-04","cited_by_count":2,"area":null},{"id":"2405.17523","title":"Locally Testing Model Detections for Semantic Global Concepts","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2411.15605","title":"GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2501.13818","title":"Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2503.06084","title":"Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2503.13429","title":"Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2504.10833","title":"Measuring the (Un)Faithfulness of Concept-Based Explanations","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2507.11099","title":"A Survey on Interpretability in Visual Recognition","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2605.13675","title":"Characterizing Universal Object Representations Across Vision Models","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2405.09580","title":"Error-margin Analysis for Hidden Neuron Activation Labels","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2405.16082","title":"Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets","created":"2024-05-25","cited_by_count":1,"area":null},{"id":"2407.04710","title":"Visual Evaluative AI: A Hypothesis-Driven Tool with Concept-Based Explanations and Weight of Evidence","created":"2024-05-13","cited_by_count":1,"area":null},{"id":"2408.08652","title":"TextCAVs: Debugging vision models using text","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2409.17109","title":"Unveiling Ontological Commitment in Multi-Modal Foundation Models","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.12439","title":"Beyond Attribution: Unified Concept-Level Explanations","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2410.18705","title":"Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2503.05522","title":"Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations","created":"2025-03-07","cited_by_count":1,"area":"mechinterp"},{"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":"2505.20293","title":"Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2509.20899","title":"Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classification","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2512.07245","title":"Zero-Shot Textual Explanations via Translating Decision-Critical Features","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2512.09730","title":"Interpreto: An Explainability Library for Transformers","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2603.13884","title":"SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis","created":"2026-03-14","cited_by_count":1,"area":"lr"},{"id":"2606.09653","title":"A Unifying Framework for Concept-Based Representational Similarity","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2201.11808","title":"LAP: An Attention-Based Module for Concept Based Self-Interpretation and Knowledge Injection in Convolutional Neural Networks","created":"2022-01-27","cited_by_count":0,"area":null},{"id":"2205.10724","title":"Learnable Visual Words for Interpretable Image Recognition","created":"2022-05-22","cited_by_count":0,"area":null},{"id":"2305.10121","title":"FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks","created":"2023-05-17","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":"2403.16782","title":"The Anatomy of Adversarial Attacks: Concept-based XAI Dissection","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2406.05598","title":"Understanding Inhibition Through Maximally Tense Images","created":"2024-06-08","cited_by_count":0,"area":null},{"id":"2410.00524","title":"Deep Model Interpretation with Limited Data : A Coreset-based Approach","created":"2024-10-01","cited_by_count":0,"area":null}],"next_cursor":"100"}