{"total":104,"rows":[{"id":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312,"area":null},{"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":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196,"area":null},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147,"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":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108,"area":null},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67,"area":null},{"id":"2302.14233","title":"Goal Driven Discovery of Distributional Differences via Language Descriptions","created":"2023-02-28","cited_by_count":62,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2305.13749","title":"Goal-Driven Explainable Clustering via Language Descriptions","created":"2023-05-23","cited_by_count":58,"area":null},{"id":"2201.12323","title":"Describing Differences between Text Distributions with Natural Language","created":"2022-01-28","cited_by_count":54,"area":null},{"id":"2312.02974","title":"Describing Differences in Image Sets with Natural Language","created":"2023-12-05","cited_by_count":53,"area":null},{"id":"2308.01544","title":"Multimodal Neurons in Pretrained Text-Only Transformers","created":"2023-08-03","cited_by_count":49,"area":null},{"id":"2409.01659","title":"Interpreting and Improving Large Language Models in Arithmetic Calculation","created":"2024-09-03","cited_by_count":45,"area":null},{"id":"2506.08010","title":"Vision Transformers Don't Need Trained Registers","created":"2025-06-09","cited_by_count":41,"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":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"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":"2511.08579","title":"Training Language Models to Explain Their Own Computations","created":"2025-11-11","cited_by_count":30,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2306.02879","title":"Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization","created":"2023-06-05","cited_by_count":28,"area":null},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"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":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"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":"2302.03629","title":"Ethical Considerations for Responsible Data Curation","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","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":"2206.04530","title":"DORA: Exploring Outlier Representations in Deep Neural Networks","created":"2022-06-09","cited_by_count":14,"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":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13,"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":"2404.14349","title":"Automatic Discovery of Visual Circuits","created":"2024-04-22","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":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2512.15712","title":"Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants","created":"2025-12-17","cited_by_count":12,"area":null},{"id":"2310.07325","title":"An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L","created":"2023-10-11","cited_by_count":11,"area":null},{"id":"2310.10591","title":"Interpreting and Controlling Vision Foundation Models via Text Explanations","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2406.01352","title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2306.08042","title":"FLamE: Few-shot Learning from Natural Language Explanations","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2309.01617","title":"DeViL: Decoding Vision features into Language","created":"2023-09-04","cited_by_count":10,"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":"2509.21972","title":"From Superficial Outputs to Superficial Learning: Risks of Large Language Models in Education","created":"2025-09-26","cited_by_count":9,"area":null},{"id":"2310.04929","title":"DISCOVER: Making Vision Networks Interpretable via Competition and Dissection","created":"2023-10-07","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":"2407.20899","title":"Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2503.09046","title":"Discovering Influential Neuron Path in Vision Transformers","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2211.10024","title":"Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks","created":"2022-11-18","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":"2206.13498","title":"Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior","created":"2022-06-27","cited_by_count":5,"area":null},{"id":"2310.10708","title":"Automated Natural Language Explanation of Deep Visual Neurons with Large Models","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2401.10217","title":"Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions","created":"2024-01-18","cited_by_count":5,"area":null},{"id":"2512.07404","title":"On LLMs' Internal Representation of Code Correctness","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":"2203.01881","title":"Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features","created":"2022-03-03","cited_by_count":4,"area":null},{"id":"2308.06755","title":"Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining","created":"2023-08-13","cited_by_count":4,"area":null},{"id":"2311.17228","title":"Survey on AI Ethics: A Socio-technical Perspective","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2405.01825","title":"Improving Concept Alignment in Vision-Language Concept Bottleneck Models","created":"2024-05-03","cited_by_count":4,"area":null},{"id":"2502.13606","title":"LaVCa: LLM-assisted Visual Cortex Captioning","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2401.06122","title":"Manipulating Feature Visualizations with Gradient Slingshots","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2404.02949","title":"The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability","created":"2024-04-03","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":"2304.13346","title":"Concept-Monitor: Understanding DNN training through individual neurons","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2310.16332","title":"Corrupting Neuron Explanations of Deep Visual Features","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2406.17241","title":"Understanding Language Model Circuits through Knowledge Editing","created":"2024-06-25","cited_by_count":2,"area":null},{"id":"2411.18651","title":"Verbalized Representation Learning for Interpretable Few-Shot Generalization","created":"2024-11-27","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":"2502.16733","title":"Coreset Selection via LLM-based Concept Bottlenecks","created":"2025-02-23","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":"2510.06378","title":"Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.21704","title":"Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2311.10933","title":"Representing visual classification as a linear combination of words","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2410.16443","title":"Improving Neuron-level Interpretability with White-box Language Models","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2508.00784","title":"Unraveling Hidden Representations: A Multi-Modal Layer Analysis for Better Synthetic Content Forensics","created":"2025-08-01","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":"2512.07245","title":"Zero-Shot Textual Explanations via Translating Decision-Critical Features","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2606.19317","title":"Explaining Attention with Program Synthesis","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2607.16232","title":"From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2211.06843","title":"Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning","created":"2022-11-13","cited_by_count":0,"area":null},{"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},{"id":"2310.07184","title":"NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2401.02744","title":"MAMI: Multi-Attentional Mutual-Information for Long Sequence Neuron Captioning","created":"2024-01-05","cited_by_count":0,"area":null},{"id":"2402.04440","title":"Exploring higher-order neural network node interactions with total correlation","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2406.01365","title":"From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2507.02241","title":"VERBA: Verbalizing Model Differences Using Large Language Models","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2509.19943","title":"Interpreting ResNet-based CLIP via Neuron-Attention Decomposition","created":"2025-09-24","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":"2603.08639","title":"UNBOX: Unveiling Black-box visual models with Natural-language","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.24953","title":"Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.22477","title":"Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples","created":"2026-04-24","cited_by_count":0,"area":null}],"next_cursor":"100"}