{"total":109,"rows":[{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"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":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65,"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":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49,"area":"mechinterp"},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"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":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2404.06453","title":"PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits","created":"2024-04-09","cited_by_count":29,"area":"mechinterp"},{"id":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2406.10995","title":"Concept-skill Transferability-based Data Selection for Large Vision-Language Models","created":"2024-06-16","cited_by_count":24,"area":"mllm"},{"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":"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":"2512.19941","title":"Block-Recurrent Dynamics in Vision Transformers","created":"2025-12-23","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":"2501.03012","title":"Analyzing Finetuning Representation Shift for Multimodal LLMs Steering","created":"2025-01-06","cited_by_count":16,"area":"mllm"},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","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":"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":"2408.12568","title":"Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers","created":"2024-08-22","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":"2404.18533","title":"Evaluating Readability and Faithfulness of Concept-based Explanations","created":"2024-04-29","cited_by_count":10,"area":null},{"id":"2505.24492","title":"Object Centric Concept Bottlenecks","created":"2025-05-30","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":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","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":"2510.11675","title":"FACE: Faithful Automatic Concept Extraction","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2502.11100","title":"Towards Achieving Concept Completeness for Textual Concept Bottleneck Models","created":"2025-02-16","cited_by_count":7,"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":"2505.20229","title":"From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance","created":"2025-05-26","cited_by_count":6,"area":"mechinterp"},{"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":"2404.09601","title":"Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2411.03993","title":"Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and dictionary-based representations","created":"2024-11-06","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":"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":"2503.18629","title":"Towards Human-Understandable Multi-Dimensional Concept Discovery","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2408.13438","title":"Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations","created":"2024-08-24","cited_by_count":3,"area":null},{"id":"2505.16077","title":"Ensembling Sparse Autoencoders","created":"2025-05-21","cited_by_count":3,"area":"mechinterp"},{"id":"2509.03738","title":"Mechanistic Interpretability with Sparse Autoencoder Neural Operators","created":"2025-09-03","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":"2604.08764","title":"Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2406.00611","title":"DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation","created":"2024-06-02","cited_by_count":2,"area":null},{"id":"2411.10019","title":"Towards Utilising a Range of Neural Activations for Comprehending Representational Associations","created":"2024-11-15","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":"2503.10643","title":"Synthetic Categorical Restructuring large Or How AIs Gradually Extract Efficient Regularities from Their Experience of the World","created":"2025-02-25","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":"2504.21307","title":"The Linear Geometry of Interpretable Tokens: Jailbreaking Attacks and Defenses for Unlearned Diffusion Models","created":"2025-04-30","cited_by_count":2,"area":"diffusion"},{"id":"2505.21032","title":"FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion models","created":"2025-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2507.17456","title":"Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection","created":"2025-07-23","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":"2605.13675","title":"Characterizing Universal Object Representations Across Vision Models","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2409.01610","title":"Decompose the model: Mechanistic interpretability in image models with Generalized Integrated Gradients (GIG)","created":"2024-09-03","cited_by_count":1,"area":"mechinterp"},{"id":"2410.12439","title":"Beyond Attribution: Unified Concept-Level Explanations","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2410.24050","title":"A Mechanistic Study of Transformers Training Dynamics","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2501.06059","title":"COMIX: Compositional Explanations using Prototypes","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2505.11576","title":"Concept-Guided Interpretability via Neural Chunking","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2506.05239","title":"Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit","created":"2025-06-05","cited_by_count":1,"area":"mechinterp"},{"id":"2507.05810","title":"Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs","created":"2025-07-08","cited_by_count":1,"area":"mechinterp"},{"id":"2507.18512","title":"Explaining How Visual, Textual and Multimodal Encoders Share Concepts","created":"2025-07-24","cited_by_count":1,"area":"mechinterp"},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2511.17735","title":"Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders","created":"2025-11-21","cited_by_count":1,"area":"mechinterp"},{"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":"2512.11433","title":"Back to the Baseline: Examining Baseline Effects on Explainability Metrics","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2602.02739","title":"TopoPrune: Robust Data Pruning via Unified Latent Space Topology","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.03319","title":"Automated Concept Discovery for LLM-as-a-Judge Preference Analysis","created":"2026-02-09","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":"2605.00474","title":"From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models","created":"2026-05-01","cited_by_count":1,"area":"mechinterp"},{"id":"2605.17504","title":"A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle","created":"2026-05-17","cited_by_count":1,"area":"mechinterp"},{"id":"2606.02061","title":"Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design","created":"2026-06-01","cited_by_count":1,"area":"mechinterp"},{"id":"2606.09653","title":"A Unifying Framework for Concept-Based Representational Similarity","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.22994","title":"Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?","created":"2026-06-22","cited_by_count":1,"area":"mechinterp"},{"id":"2607.01303","title":"CPG-PAD: Concept-Informed Prompts Guided Presentation Attack Detection","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.15323","title":"When Do Concepts Become Functionally Sufficient During Language-Model Training?","created":"2026-08-15","cited_by_count":1,"area":null},{"id":"2406.05598","title":"Understanding Inhibition Through Maximally Tense Images","created":"2024-06-08","cited_by_count":0,"area":null},{"id":"2409.10733","title":"BaTCAVe: Trustworthy Explanations for Robot Behaviors","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2410.12511","title":"Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2411.18645","title":"Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2503.03443","title":"Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertainty","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2503.12992","title":"Intra-neuronal attention within language models Relationships between activation and semantics","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2505.07831","title":"Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2505.21589","title":"Do you see what I see? An Ambiguous Optical Illusion Dataset exposing limitations of Explainable AI","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2505.23917","title":"Representational Difference Explanations","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.11263","title":"Features Emerge as Discrete States: The First Application of SAEs to 3D Representations","created":"2025-12-12","cited_by_count":0,"area":"mechinterp"},{"id":"2512.19734","title":"The Deleuzian Representation Hypothesis","created":"2025-12-17","cited_by_count":0,"area":"mechinterp"},{"id":"2601.12303","title":"Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2603.06557","title":"Causal Interpretation of Neural Network Computations with Contribution Decomposition","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.27055","title":"Text Data Integration","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2605.15688","title":"$\\alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.20337","title":"Capability $\\neq$ Interpretability: Human Interpretability of Vision Foundation Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.29628","title":"COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.03695","title":"Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":"100"}