{"total":1119,"rows":[{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716,"area":null},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431,"area":null},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293,"area":null},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285,"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":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"area":null},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"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":"2107.10912","title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","created":"2021-07-22","cited_by_count":147,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137,"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":"2106.13314","title":"Promises and Pitfalls of Black-Box Concept Learning Models","created":"2021-06-24","cited_by_count":131,"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":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125,"area":null},{"id":"2110.10790","title":"Human-Centered Explainable AI (XAI): From Algorithms to User Experiences","created":"2021-10-20","cited_by_count":123,"area":null},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"area":null},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","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":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102,"area":null},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2306.01574","title":"Probabilistic Concept Bottleneck Models","created":"2023-06-02","cited_by_count":101,"area":null},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97,"area":null},{"id":"2112.02902","title":"Interpretable Image Classification with Differentiable Prototypes Assignment","created":"2021-12-06","cited_by_count":97,"area":null},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91,"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":"2301.03028","title":"Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement","created":"2023-01-08","cited_by_count":90,"area":null},{"id":"2403.18932","title":"Measuring Political Bias in Large Language Models: What Is Said and How It Is Said","created":"2024-03-27","cited_by_count":89,"area":null},{"id":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88,"area":null},{"id":"2210.11584","title":"Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations","created":"2022-10-20","cited_by_count":85,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2105.03761","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","created":"2021-05-08","cited_by_count":84,"area":null},{"id":"2111.02398","title":"Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods","created":"2021-11-01","cited_by_count":83,"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":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"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":"2202.01459","title":"Concept Bottleneck Model with Additional Unsupervised Concepts","created":"2022-02-03","cited_by_count":79,"area":null},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"area":null},{"id":"2206.01254","title":"Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations","created":"2022-06-02","cited_by_count":77,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2103.10663","title":"XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations","created":"2021-03-19","cited_by_count":73,"area":null},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73,"area":null},{"id":"2301.07255","title":"Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations","created":"2023-01-18","cited_by_count":73,"area":null},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71,"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":"2105.02968","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","created":"2021-05-05","cited_by_count":65,"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":"2210.07147","title":"Global Explainability of GNNs via Logic Combination of Learned Concepts","created":"2022-10-13","cited_by_count":65,"area":null},{"id":"2101.09824","title":"Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs","created":"2021-01-24","cited_by_count":64,"area":null},{"id":"2302.14260","title":"A Closer Look at the Intervention Procedure of Concept Bottleneck Models","created":"2023-02-28","cited_by_count":64,"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":"2210.03735","title":"\"Help Me Help the AI\": Understanding How Explainability Can Support Human-AI Interaction","created":"2022-10-02","cited_by_count":63,"area":null},{"id":"2305.07961","title":"Leveraging Large Language Models in Conversational Recommender Systems","created":"2023-05-13","cited_by_count":63,"area":null},{"id":"2104.07411","title":"NICE: An Algorithm for Nearest Instance Counterfactual Explanations","created":"2021-04-15","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":"2209.09056","title":"Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off","created":"2022-09-19","cited_by_count":61,"area":null},{"id":"2105.06965","title":"Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction","created":"2021-05-14","cited_by_count":59,"area":null},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2101.08758","title":"How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations","created":"2021-01-21","cited_by_count":58,"area":null},{"id":"2206.07835","title":"Disentangling visual and written concepts in CLIP","created":"2022-06-15","cited_by_count":58,"area":null},{"id":"2209.11222","title":"Concept Activation Regions: A Generalized Framework For Concept-Based Explanations","created":"2022-09-22","cited_by_count":57,"area":null},{"id":"2304.14068","title":"Interpretable Neural-Symbolic Concept Reasoning","created":"2023-04-27","cited_by_count":57,"area":null},{"id":"2201.10766","title":"A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes","created":"2022-01-26","cited_by_count":56,"area":null},{"id":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"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":"2106.12723","title":"Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations","created":"2021-06-24","cited_by_count":53,"area":null},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52,"area":null},{"id":"2106.06804","title":"Entropy-based Logic Explanations of Neural Networks","created":"2021-06-12","cited_by_count":51,"area":null},{"id":"2406.19272","title":"Stochastic Concept Bottleneck Models","created":"2024-06-27","cited_by_count":51,"area":null},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","cited_by_count":50,"area":null},{"id":"2308.06248","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","created":"2023-08-11","cited_by_count":50,"area":null},{"id":"2104.12669","title":"Exploiting Explanations for Model Inversion Attacks","created":"2021-04-26","cited_by_count":49,"area":null},{"id":"2304.10131","title":"Learning Bottleneck Concepts in Image Classification","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2201.12191","title":"Kernelized Concept Erasure","created":"2022-01-28","cited_by_count":48,"area":null},{"id":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2102.10618","title":"Towards the Unification and Robustness of Perturbation and Gradient Based Explanations","created":"2021-02-21","cited_by_count":47,"area":null},{"id":"2402.13055","title":"Identifying Semantic Induction Heads to Understand In-Context Learning","created":"2024-02-20","cited_by_count":47,"area":null},{"id":"2207.09615","title":"Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability","created":"2022-07-20","cited_by_count":46,"area":null},{"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":"2406.07882","title":"Designing a Dashboard for Transparency and Control of Conversational AI","created":"2024-06-12","cited_by_count":46,"area":null},{"id":"2103.14651","title":"Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice","created":"2021-03-27","cited_by_count":45,"area":null},{"id":"2108.05149","title":"Logic Explained Networks","created":"2021-08-11","cited_by_count":45,"area":null},{"id":"2108.11761","title":"A Framework for Learning Ante-hoc Explainable Models via Concepts","created":"2021-08-25","cited_by_count":45,"area":null},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45,"area":null},{"id":"2504.00125","title":"LLMs for Explainable AI: A Comprehensive Survey","created":"2025-03-31","cited_by_count":45,"area":null}],"next_cursor":"100"}