{"total":135,"rows":[{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293,"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":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"area":null},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"area":null},{"id":"2104.13369","title":"Explaining in Style: Training a GAN to explain a classifier in StyleSpace","created":"2021-04-27","cited_by_count":122,"area":null},{"id":"2101.06046","title":"Counterfactual Generative Networks","created":"2021-01-15","cited_by_count":111,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2108.00783","title":"CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms","created":"2021-08-02","cited_by_count":86,"area":null},{"id":"2105.04857","title":"Leveraging Sparse Linear Layers for Debuggable Deep Networks","created":"2021-05-11","cited_by_count":82,"area":null},{"id":"2202.01459","title":"Concept Bottleneck Model with Additional Unsupervised Concepts","created":"2022-02-03","cited_by_count":79,"area":null},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65,"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":"2106.06804","title":"Entropy-based Logic Explanations of Neural Networks","created":"2021-06-12","cited_by_count":51,"area":null},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45,"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":"2103.05825","title":"ELLA: Exploration through Learned Language Abstraction","created":"2021-03-10","cited_by_count":42,"area":null},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2309.16928","title":"Learning to Receive Help: Intervention-Aware Concept Embedding Models","created":"2023-09-29","cited_by_count":41,"area":null},{"id":"2105.14002","title":"What if This Modified That? Syntactic Interventions via Counterfactual Embeddings","created":"2021-05-28","cited_by_count":39,"area":null},{"id":"2105.15164","title":"DISSECT: Disentangled Simultaneous Explanations via Concept Traversals","created":"2021-05-31","cited_by_count":37,"area":null},{"id":"2305.10289","title":"Explain Any Concept: Segment Anything Meets Concept-Based Explanation","created":"2023-05-17","cited_by_count":37,"area":null},{"id":"2203.15064","title":"Cycle-Consistent Counterfactuals by Latent Transformations","created":"2022-03-28","cited_by_count":33,"area":null},{"id":"2311.05014","title":"Interpreting Pretrained Language Models via Concept Bottlenecks","created":"2023-11-08","cited_by_count":33,"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":"2405.16507","title":"Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning","created":"2024-05-26","cited_by_count":29,"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":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2202.02896","title":"Evaluation Methods and Measures for Causal Learning Algorithms","created":"2022-02-07","cited_by_count":23,"area":null},{"id":"2202.12451","title":"Human-Centered Concept Explanations for Neural Networks","created":"2022-02-25","cited_by_count":23,"area":null},{"id":"2208.10244","title":"Unit Testing for Concepts in Neural Networks","created":"2022-07-28","cited_by_count":23,"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":"2112.05746","title":"On Causally Disentangled Representations","created":"2021-12-10","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":"2203.13909","title":"Concept Embedding Analysis: A Review","created":"2022-03-25","cited_by_count":20,"area":null},{"id":"2208.14966","title":"Concept Gradient: Concept-based Interpretation Without Linear Assumption","created":"2022-08-31","cited_by_count":20,"area":null},{"id":"2403.09683","title":"Counterfactual Image Editing","created":"2024-02-07","cited_by_count":20,"area":null},{"id":"2105.04837","title":"Rationalization through Concepts","created":"2021-05-11","cited_by_count":19,"area":null},{"id":"2209.15093","title":"Unpacking Large Language Models with Conceptual Consistency","created":"2022-09-29","cited_by_count":18,"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":"2503.04363","title":"Causally Reliable Concept Bottleneck Models","created":"2025-03-06","cited_by_count":17,"area":null},{"id":"2206.04531","title":"ECLAD: Extracting Concepts with Local Aggregated Descriptors","created":"2022-06-09","cited_by_count":15,"area":null},{"id":"2307.14517","title":"The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers","created":"2023-07-26","cited_by_count":15,"area":null},{"id":"2106.08971","title":"Model-Based Counterfactual Synthesizer for Interpretation","created":"2021-06-16","cited_by_count":14,"area":null},{"id":"2108.09451","title":"Learn-Explain-Reinforce: Counterfactual Reasoning and Its Guidance to Reinforce an Alzheimer's Disease Diagnosis Model","created":"2021-08-21","cited_by_count":14,"area":null},{"id":"2112.04895","title":"Latent Space Explanation by Intervention","created":"2021-12-09","cited_by_count":13,"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":"2206.05275","title":"Spatial-temporal Concept based Explanation of 3D ConvNets","created":"2022-06-09","cited_by_count":12,"area":null},{"id":"2212.11254","title":"Adapting to Latent Subgroup Shifts via Concepts and Proxies","created":"2022-12-21","cited_by_count":12,"area":null},{"id":"2307.13992","title":"Causal reasoning in typical computer vision tasks","created":"2023-07-26","cited_by_count":12,"area":"lr"},{"id":"2204.04601","title":"Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention","created":"2022-04-10","cited_by_count":11,"area":null},{"id":"2212.13261","title":"Explainable AI for Bioinformatics: Methods, Tools, and Applications","created":"2022-12-25","cited_by_count":11,"area":null},{"id":"2508.21422","title":"Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework","created":"2025-08-29","cited_by_count":11,"area":"lr"},{"id":"2111.12490","title":"Matching Learned Causal Effects of Neural Networks with Domain Priors","created":"2021-11-24","cited_by_count":10,"area":null},{"id":"2401.01259","title":"Do Concept Bottleneck Models Respect Localities?","created":"2024-01-02","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":"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":"2105.07033","title":"Cause and Effect: Hierarchical Concept-based Explanation of Neural Networks","created":"2021-05-14","cited_by_count":8,"area":null},{"id":"2109.04518","title":"Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation","created":"2021-09-09","cited_by_count":8,"area":null},{"id":"2206.08500","title":"What do navigation agents learn about their environment?","created":"2022-06-17","cited_by_count":8,"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":"2111.11165","title":"Graph-Based Similarity of Neural Network Representations","created":"2021-11-22","cited_by_count":7,"area":null},{"id":"2305.15775","title":"Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2402.01408","title":"Counterfactual Concept Bottleneck Models","created":"2024-02-02","cited_by_count":7,"area":null},{"id":"2101.07086","title":"Model Compression for Domain Adaptation through Causal Effect Estimation","created":"2021-01-18","cited_by_count":6,"area":null},{"id":"2403.07442","title":"Proxy Methods for Domain Adaptation","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2502.06536","title":"Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2110.11929","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","created":"2021-10-22","cited_by_count":5,"area":null},{"id":"2304.10346","title":"Interventional Probing in High Dimensions: An NLI Case Study","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2307.06913","title":"Uncovering Unique Concept Vectors through Latent Space Decomposition","created":"2023-07-13","cited_by_count":5,"area":null},{"id":"2401.08534","title":"DiConStruct: Causal Concept-based Explanations through Black-Box Distillation","created":"2024-01-16","cited_by_count":5,"area":"distill"},{"id":"2103.13455","title":"Matched sample selection with GANs for mitigating attribute confounding","created":"2021-03-24","cited_by_count":4,"area":null},{"id":"2206.05257","title":"Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces","created":"2022-06-10","cited_by_count":4,"area":null},{"id":"2305.18362","title":"Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2402.07419","title":"Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2405.15871","title":"Explaining Time Series Classification Predictions via Causal Attributions","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2508.00545","title":"Foundations of Interpretable Models","created":"2025-08-01","cited_by_count":4,"area":null},{"id":"2203.16475","title":"Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and Discoveries","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2207.11231","title":"Learning Unsupervised Hierarchies of Audio Concepts","created":"2022-07-21","cited_by_count":3,"area":null},{"id":"2211.14797","title":"Latent SHAP: Toward Practical Human-Interpretable Explanations","created":"2022-11-27","cited_by_count":3,"area":null},{"id":"2405.00349","title":"A Self-explaining Neural Architecture for Generalizable Concept Learning","created":"2024-05-01","cited_by_count":3,"area":null},{"id":"2406.14335","title":"Linearly-Interpretable Concept Embedding Models for Text Analysis","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2412.18604","title":"Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models","created":"2024-12-24","cited_by_count":3,"area":"diffusion"},{"id":"2504.11159","title":"C-SHAP for time series: An approach to high-level temporal explanations","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2201.09689","title":"Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGAN","created":"2022-01-24","cited_by_count":2,"area":null},{"id":"2205.02102","title":"Concept Activation Vectors for Generating User-Defined 3D Shapes","created":"2022-04-29","cited_by_count":2,"area":null},{"id":"2303.13850","title":"Towards Learning and Explaining Indirect Causal Effects in Neural Networks","created":"2023-03-24","cited_by_count":2,"area":null},{"id":"2306.03551","title":"Scalable Concept Extraction in Industry 4.0","created":"2023-06-06","cited_by_count":2,"area":null},{"id":"2308.06022","title":"Scale-Preserving Automatic Concept Extraction (SPACE)","created":"2023-08-11","cited_by_count":2,"area":null},{"id":"2308.08407","title":"Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2402.09197","title":"Implementing local-explainability in Gradient Boosting Trees: Feature Contribution","created":"2024-02-14","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":"2404.12341","title":"Measuring Feature Dependency of Neural Networks by Collapsing Feature Dimensions in the Data Manifold","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2407.19300","title":"CoLiDR: Concept Learning using Aggregated Disentangled Representations","created":"2024-07-27","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":"2503.05424","title":"Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients","created":"2025-03-07","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":"2601.10700","title":"LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2602.00092","title":"Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits","created":"2026-01-23","cited_by_count":2,"area":null},{"id":"2110.07778","title":"NeuroView: Explainable Deep Network Decision Making","created":"2021-10-15","cited_by_count":1,"area":null}],"next_cursor":"100"}