{"total":147,"rows":[{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285,"area":null},{"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":"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":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"area":"mllm"},{"id":"2408.01432","title":"VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance","created":"2024-07-18","cited_by_count":65,"area":null},{"id":"2305.06386","title":"Text-To-Concept (and Back) via Cross-Model Alignment","created":"2023-05-10","cited_by_count":64,"area":null},{"id":"2404.14394","title":"A Multimodal Automated Interpretability Agent","created":"2024-04-22","cited_by_count":63,"area":"agents"},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"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":"2412.07992","title":"Concept Bottleneck Large Language Models","created":"2024-12-11","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":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2307.10504","title":"Identifying Interpretable Subspaces in Image Representations","created":"2023-07-20","cited_by_count":32,"area":null},{"id":"2309.03886","title":"FIND: A Function Description Benchmark for Evaluating Interpretability Methods","created":"2023-09-07","cited_by_count":32,"area":null},{"id":"2311.13594","title":"Labeling Neural Representations with Inverse Recognition","created":"2023-11-22","cited_by_count":32,"area":null},{"id":"2310.02116","title":"Coarse-to-Fine Concept Bottleneck Models","created":"2023-10-03","cited_by_count":31,"area":null},{"id":"2406.11193","title":"MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model","created":"2024-06-17","cited_by_count":26,"area":"mllm"},{"id":"2503.24071","title":"From Colors to Classes: Emergence of Concepts in Vision Transformers","created":"2025-03-31","cited_by_count":23,"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":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2405.06855","title":"Linear Explanations for Individual Neurons","created":"2024-05-10","cited_by_count":19,"area":null},{"id":"2405.20331","title":"CoSy: Evaluating Textual Explanations of Neurons","created":"2024-05-30","cited_by_count":17,"area":null},{"id":"2406.00519","title":"Learning Discrete Concepts in Latent Hierarchical Models","created":"2024-06-01","cited_by_count":17,"area":null},{"id":"2410.04368","title":"Algorithmic Capabilities of Random Transformers","created":"2024-10-06","cited_by_count":17,"area":null},{"id":"2406.05191","title":"DiffusionPID: Interpreting Diffusion via Partial Information Decomposition","created":"2024-06-07","cited_by_count":16,"area":"diffusion"},{"id":"2310.18443","title":"Towards a fuller understanding of neurons with Clustered Compositional Explanations","created":"2023-10-27","cited_by_count":15,"area":null},{"id":"2402.18956","title":"WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts","created":"2024-02-29","cited_by_count":14,"area":null},{"id":"2310.11884","title":"From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks","created":"2023-10-18","cited_by_count":13,"area":null},{"id":"2310.06200","title":"The Importance of Prompt Tuning for Automated Neuron Explanations","created":"2023-10-09","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":"2405.16714","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","created":"2024-05-26","cited_by_count":11,"area":null},{"id":"2503.19377","title":"Interpretable Generative Models through Post-hoc Concept Bottlenecks","created":"2025-03-25","cited_by_count":11,"area":null},{"id":"2403.13771","title":"Interpreting Neurons in Deep Vision Networks with Language Models","created":"2024-03-20","cited_by_count":10,"area":null},{"id":"2410.10308","title":"LG-CAV: Train Any Concept Activation Vector with Language Guidance","created":"2024-10-14","cited_by_count":9,"area":"mllm"},{"id":"2412.14097","title":"Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2501.04975","title":"V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer","created":"2025-01-09","cited_by_count":9,"area":null},{"id":"2503.15234","title":"CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2503.21730","title":"Effective Skill Unlearning through Intervention and Abstention","created":"2025-03-27","cited_by_count":9,"area":"safety"},{"id":"2310.04929","title":"DISCOVER: Making Vision Networks Interpretable via Competition and Dissection","created":"2023-10-07","cited_by_count":8,"area":null},{"id":"2407.04307","title":"Crafting Large Language Models for Enhanced Interpretability","created":"2024-07-05","cited_by_count":8,"area":null},{"id":"2306.07397","title":"Adversarial Attacks on the Interpretation of Neuron Activation Maximization","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2406.16990","title":"AND: Audio Network Dissection for Interpreting Deep Acoustic Models","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2407.12543","title":"Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2410.04819","title":"MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models","created":"2024-10-07","cited_by_count":7,"area":"mllm"},{"id":"2503.09046","title":"Discovering Influential Neuron Path in Vision Transformers","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2510.05782","title":"Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection","created":"2025-10-07","cited_by_count":7,"area":null},{"id":"2310.13040","title":"Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts","created":"2023-10-19","cited_by_count":6,"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":"2406.08572","title":"LLM-assisted Concept Discovery: Automatically Identifying and Explaining Neuron Functions","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6,"area":"mechinterp"},{"id":"2312.10747","title":"CEIR: Concept-based Explainable Image Representation Learning","created":"2023-12-17","cited_by_count":5,"area":null},{"id":"2404.16482","title":"CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representations","created":"2024-04-25","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":"2508.01728","title":"Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations","created":"2025-08-03","cited_by_count":5,"area":"mechinterp"},{"id":"2510.26186","title":"ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2511.22170","title":"Partially Shared Concept Bottleneck Models","created":"2025-11-27","cited_by_count":5,"area":null},{"id":"2512.07383","title":"LogicCBMs: Logic-Enhanced Concept-Based Learning","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2512.08560","title":"BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain","created":"2025-12-09","cited_by_count":5,"area":null},{"id":"2502.13606","title":"LaVCa: LLM-assisted Visual Cortex Captioning","created":"2025-02-19","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":"2310.07837","title":"Measuring Feature Sparsity in Language Models","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2405.19146","title":"I Bet You Did Not Mean That: Testing Semantic Importance via Betting","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2409.15190","title":"Interpretability-Guided Test-Time Adversarial Defense","created":"2024-09-23","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":"2502.18485","title":"Deciphering Functions of Neurons in Vision-Language Models","created":"2025-02-10","cited_by_count":3,"area":"mllm"},{"id":"2506.05286","title":"Stable Vision Concept Transformers for Medical Diagnosis","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2510.01048","title":"Interpreting Language Models Through Concept Descriptions: A Survey","created":"2025-10-01","cited_by_count":3,"area":"mechinterp"},{"id":"2510.27413","title":"Atlas-Alignment: Making Interpretability Transferable Across Language Models","created":"2025-10-31","cited_by_count":3,"area":"mechinterp"},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2512.18092","title":"Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability","created":"2025-12-19","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":"2606.06664","title":"Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers","created":"2026-06-04","cited_by_count":3,"area":"mechinterp"},{"id":"2304.13346","title":"Concept-Monitor: Understanding DNN training through individual neurons","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2312.17285","title":"Understanding Distributed Representations of Concepts in Deep Neural Networks without Supervision","created":"2023-12-28","cited_by_count":2,"area":null},{"id":"2501.05205","title":"Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning","created":"2025-01-09","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":"2502.20130","title":"QPM: Discrete Optimization for Globally Interpretable Image Classification","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2505.06123","title":"Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomena","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2506.01247","title":"Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering","created":"2025-06-02","cited_by_count":2,"area":"mechinterp"},{"id":"2511.03725","title":"Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition","created":"2025-11-05","cited_by_count":2,"area":null},{"id":"2601.20075","title":"Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning","created":"2026-01-27","cited_by_count":2,"area":"mllm"},{"id":"2602.20853","title":"On the Explainability of Vision-Language Models in Art History","created":"2026-02-24","cited_by_count":2,"area":"mllm"},{"id":"2405.09580","title":"Error-margin Analysis for Hidden Neuron Activation Labels","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2504.13140","title":"PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2507.05810","title":"Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs","created":"2025-07-08","cited_by_count":1,"area":"mechinterp"},{"id":"2508.16937","title":"NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2509.23849","title":"CE-FAM: Concept-Based Explanation via Fusion of Activation Maps","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","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":"2601.22157","title":"Discovering Hidden Gems in Model Repositories","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.09787","title":"What is Missing? Explaining Neurons Activated by Absent Concepts","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2604.02468","title":"Hierarchical, Interpretable, Label-Free Concept Bottleneck Model","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2606.03990","title":"Neuron Populations Exhibit Divergent Selectivity with Scale","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.24997","title":"What's in an Earth Embedding? An Explainability Analysis of Location Encoders","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.04548","title":"Explainable Novel Category Discovery in Semantic Concept Space","created":"2026-07-05","cited_by_count":1,"area":null},{"id":"2607.08605","title":"When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities","created":"2026-07-09","cited_by_count":1,"area":"mechinterp"},{"id":"2308.12562","title":"Variational Information Pursuit with Large Language and Multimodal Models for Interpretable Predictions","created":"2023-08-24","cited_by_count":0,"area":null}],"next_cursor":"100"}