{"total":160,"rows":[{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101,"area":null},{"id":"2308.01862","title":"Wider and Deeper LLM Networks are Fairer LLM Evaluators","created":"2023-08-03","cited_by_count":94,"area":null},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91,"area":null},{"id":"2305.15054","title":"A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis","created":"2023-05-24","cited_by_count":89,"area":"lr"},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2106.05303","title":"Explaining Time Series Predictions with Dynamic Masks","created":"2021-06-09","cited_by_count":73,"area":null},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66,"area":null},{"id":"2404.14394","title":"A Multimodal Automated Interpretability Agent","created":"2024-04-22","cited_by_count":63,"area":"agents"},{"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":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53,"area":null},{"id":"2106.15339","title":"SpreadsheetCoder: Formula Prediction from Semi-structured Context","created":"2021-06-26","cited_by_count":41,"area":null},{"id":"2205.03295","title":"The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39,"area":null},{"id":"2206.13289","title":"Analyzing Encoded Concepts in Transformer Language Models","created":"2022-06-27","cited_by_count":38,"area":null},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2308.15419","title":"Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability","created":"2023-08-29","cited_by_count":35,"area":null},{"id":"2308.05696","title":"A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment","created":"2023-08-10","cited_by_count":33,"area":"alignment"},{"id":"2406.09415","title":"An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels","created":"2024-06-13","cited_by_count":33,"area":null},{"id":"2112.00791","title":"Controlling Conditional Language Models without Catastrophic Forgetting","created":"2021-12-01","cited_by_count":32,"area":null},{"id":"2304.05088","title":"WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition","created":"2023-04-11","cited_by_count":32,"area":null},{"id":"2108.00702","title":"Improving Deep Learning for HAR with shallow LSTMs","created":"2021-08-02","cited_by_count":30,"area":null},{"id":"2101.04109","title":"Explain and Predict, and then Predict Again","created":"2021-01-11","cited_by_count":29,"area":null},{"id":"2107.08264","title":"M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis","created":"2021-07-17","cited_by_count":29,"area":null},{"id":"2102.05486","title":"Towards More Fine-grained and Reliable NLP Performance Prediction","created":"2021-02-10","cited_by_count":26,"area":null},{"id":"2307.07712","title":"Visual Analytics For Machine Learning: A Data Perspective Survey","created":"2023-07-15","cited_by_count":25,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"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":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"area":null},{"id":"2108.00406","title":"Discovering Distinctive \"Semantics\" in Super-Resolution Networks","created":"2021-08-01","cited_by_count":20,"area":null},{"id":"2109.01401","title":"CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Models","created":"2021-09-03","cited_by_count":20,"area":null},{"id":"2406.12618","title":"From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP","created":"2024-06-18","cited_by_count":20,"area":null},{"id":"2104.00926","title":"VisQA: X-raying Vision and Language Reasoning in Transformers","created":"2021-04-02","cited_by_count":19,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2308.00189","title":"Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?","created":"2023-07-31","cited_by_count":19,"area":null},{"id":"2206.09355","title":"A Unified Understanding of Deep NLP Models for Text Classification","created":"2022-06-19","cited_by_count":18,"area":null},{"id":"2201.12451","title":"Extracting Finite Automata from RNNs Using State Merging","created":"2022-01-28","cited_by_count":17,"area":null},{"id":"2203.09258","title":"Explainability in Graph Neural Networks: An Experimental Survey","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2305.13386","title":"Can LLMs facilitate interpretation of pre-trained language models?","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2102.01792","title":"A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks","created":"2021-02-02","cited_by_count":14,"area":null},{"id":"2104.06400","title":"Mediators in Determining what Processing BERT Performs First","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2510.24963","title":"Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale","created":"2025-10-28","cited_by_count":13,"area":null},{"id":"2102.07824","title":"An Operator Theoretic Approach for Analyzing Sequence Neural Networks","created":"2021-02-15","cited_by_count":12,"area":null},{"id":"2105.02388","title":"Security Vulnerability Detection Using Deep Learning Natural Language Processing","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2110.04328","title":"Distinguishing rule- and exemplar-based generalization in learning systems","created":"2021-10-08","cited_by_count":12,"area":null},{"id":"2302.03788","title":"Toward a Theory of Causation for Interpreting Neural Code Models","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2108.13961","title":"Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools","created":"2021-08-31","cited_by_count":11,"area":null},{"id":"2110.10185","title":"GenNI: Human-AI Collaboration for Data-Backed Text Generation","created":"2021-10-19","cited_by_count":11,"area":null},{"id":"2305.17073","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2407.08983","title":"Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2106.04985","title":"Energy-Based Models for Code Generation under Compilability Constraints","created":"2021-06-09","cited_by_count":10,"area":null},{"id":"2102.10094","title":"Formal Language Theory Meets Modern NLP","created":"2021-02-19","cited_by_count":9,"area":null},{"id":"2102.12924","title":"Visualizing MuZero Models","created":"2021-02-25","cited_by_count":9,"area":null},{"id":"2110.15288","title":"Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction","created":"2021-10-28","cited_by_count":9,"area":null},{"id":"2308.03873","title":"Evaluating and Explaining Large Language Models for Code Using Syntactic Structures","created":"2023-08-07","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2104.06118","title":"Automatic Correction of Internal Units in Generative Neural Networks","created":"2021-04-13","cited_by_count":8,"area":null},{"id":"2109.10253","title":"Short-term traffic prediction using physics-aware neural networks","created":"2021-09-21","cited_by_count":8,"area":null},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2306.01117","title":"Examining the Causal Effect of First Names on Language Models: The Case of Social Commonsense Reasoning","created":"2023-06-01","cited_by_count":8,"area":"lr"},{"id":"2311.15831","title":"Temporal Action Localization for Inertial-based Human Activity Recognition","created":"2023-11-27","cited_by_count":8,"area":null},{"id":"2102.11934","title":"Feature Importance Explanations for Temporal Black-Box Models","created":"2021-02-23","cited_by_count":7,"area":null},{"id":"2105.11640","title":"Safe Model-based Off-policy Reinforcement Learning for Eco-Driving in Connected and Automated Hybrid Electric Vehicles","created":"2021-05-25","cited_by_count":7,"area":"driving"},{"id":"2108.10070","title":"A Learning-Based Fast Uplink Grant for Massive IoT via Support Vector Machines and Long Short-Term Memory","created":"2021-08-02","cited_by_count":7,"area":null},{"id":"2404.08793","title":"JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models","created":"2024-04-12","cited_by_count":7,"area":"safety"},{"id":"2412.00800","title":"A Comprehensive Guide to Explainable AI: From Classical Models to LLMs","created":"2024-12-01","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":"2103.10229","title":"Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles","created":"2021-03-18","cited_by_count":6,"area":null},{"id":"2104.11244","title":"Equivariant Wavelets: Fast Rotation and Translation Invariant Wavelet Scattering Transforms","created":"2021-04-22","cited_by_count":6,"area":null},{"id":"2112.03020","title":"Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2303.01576","title":"DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction","created":"2023-03-02","cited_by_count":6,"area":null},{"id":"2403.03028","title":"Word Importance Explains How Prompts Affect Language Model Outputs","created":"2024-03-05","cited_by_count":6,"area":null},{"id":"2407.17053","title":"Automated Code-centric Software Vulnerability Assessment: How Far Are We? An Empirical Study in C/C++","created":"2024-07-24","cited_by_count":6,"area":null},{"id":"2412.18989","title":"How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study","created":"2024-12-25","cited_by_count":6,"area":null},{"id":"2201.08214","title":"A Latent-Variable Model for Intrinsic Probing","created":"2022-01-20","cited_by_count":5,"area":null},{"id":"2204.05428","title":"A Multilingual Perspective Towards the Evaluation of Attribution Methods in Natural Language Inference","created":"2022-04-11","cited_by_count":5,"area":null},{"id":"2210.02176","title":"Feature Importance for Time Series Data: Improving KernelSHAP","created":"2022-10-05","cited_by_count":5,"area":null},{"id":"2301.00436","title":"Hierarchical Explanations for Video Action Recognition","created":"2023-01-01","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":"2410.13792","title":"Analyzing Deep Transformer Models for Time Series Forecasting via Manifold Learning","created":"2024-10-17","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":"2506.10920","title":"Constructing Interpretable Features from Compositional Neuron Groups","created":"2025-06-12","cited_by_count":5,"area":"mechinterp"},{"id":"2105.08039","title":"Fine-grained Interpretation and Causation Analysis in Deep NLP Models","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2201.11194","title":"Attention cannot be an Explanation","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2205.02724","title":"Implicit N-grams Induced by Recurrence","created":"2022-05-05","cited_by_count":4,"area":null},{"id":"2205.10238","title":"Visualizing and Explaining Language Models","created":"2022-04-30","cited_by_count":4,"area":null},{"id":"2212.12380","title":"Towards Scalable Physically Consistent Neural Networks: an Application to Data-driven Multi-zone Thermal Building Models","created":"2022-12-23","cited_by_count":4,"area":null},{"id":"2310.08164","title":"Interpreting Learned Feedback Patterns in Large Language Models","created":"2023-10-12","cited_by_count":4,"area":"alignment"},{"id":"2408.03274","title":"Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments","created":"2024-08-06","cited_by_count":4,"area":null},{"id":"2101.11335","title":"On the Interpretability of Deep Learning Based Models for Knowledge Tracing","created":"2021-01-27","cited_by_count":3,"area":null},{"id":"2201.13377","title":"Neural Network Training with Asymmetric Crosspoint Elements","created":"2022-01-31","cited_by_count":3,"area":null},{"id":"2204.04876","title":"Lyapunov-Guided Representation of Recurrent Neural Network Performance","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2210.12206","title":"Probing with Noise: Unpicking the Warp and Weft of Embeddings","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2306.17184","title":"State space models can express n-gram languages","created":"2023-06-20","cited_by_count":3,"area":null}],"next_cursor":"100"}