{"total":53,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"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":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156,"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":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"area":null},{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104,"area":null},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98,"area":null},{"id":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88,"area":null},{"id":"2103.01035","title":"If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques","created":"2021-02-26","cited_by_count":82,"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":"2206.01794","title":"Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology","created":"2022-06-03","cited_by_count":58,"area":null},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","cited_by_count":32,"area":null},{"id":"2108.01661","title":"Grounding Representation Similarity with Statistical Testing","created":"2021-08-03","cited_by_count":29,"area":null},{"id":"2106.12447","title":"How Well do Feature Visualizations Support Causal Understanding of CNN Activations?","created":"2021-06-23","cited_by_count":28,"area":null},{"id":"2202.03407","title":"Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience","created":"2022-02-07","cited_by_count":28,"area":null},{"id":"2205.15834","title":"Attribution-based Explanations that Provide Recourse Cannot be Robust","created":"2022-05-31","cited_by_count":20,"area":null},{"id":"2208.10605","title":"SoK: Explainable Machine Learning for Computer Security Applications","created":"2022-08-22","cited_by_count":20,"area":null},{"id":"2103.10005","title":"Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset","created":"2021-03-18","cited_by_count":18,"area":null},{"id":"2307.05471","title":"Scale Alone Does not Improve Mechanistic Interpretability in Vision Models","created":"2023-07-11","cited_by_count":18,"area":"mechinterp"},{"id":"2309.14531","title":"Pixel-Grounded Prototypical Part Networks","created":"2023-09-25","cited_by_count":18,"area":null},{"id":"2204.10152","title":"Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAI","created":"2022-04-21","cited_by_count":16,"area":null},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16,"area":null},{"id":"2105.06677","title":"XAI Handbook: Towards a Unified Framework for Explainable AI","created":"2021-05-14","cited_by_count":14,"area":null},{"id":"2508.09853","title":"STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2303.17707","title":"Why is plausibility surprisingly problematic as an XAI criterion?","created":"2023-03-30","cited_by_count":9,"area":null},{"id":"2310.11431","title":"Identifying Interpretable Visual Features in Artificial and Biological Neural Systems","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2305.08950","title":"Causal Analysis for Robust Interpretability of Neural Networks","created":"2023-05-15","cited_by_count":8,"area":null},{"id":"2305.14585","title":"Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models","created":"2023-05-23","cited_by_count":8,"area":null},{"id":"2407.13281","title":"Auditing Local Explanations is Hard","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2311.00863","title":"Training Dynamics of Contextual N-Grams in Language Models","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2504.02667","title":"Compositionality Unlocks Deep Interpretable Models","created":"2025-04-03","cited_by_count":6,"area":null},{"id":"2505.00808","title":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i","created":"2025-05-01","cited_by_count":6,"area":"mechinterp"},{"id":"2310.03466","title":"The Blame Problem in Evaluating Local Explanations, and How to Tackle it","created":"2023-10-05","cited_by_count":5,"area":null},{"id":"2311.11491","title":"On the Relationship Between Interpretability and Explainability in Machine Learning","created":"2023-11-20","cited_by_count":3,"area":null},{"id":"2312.05337","title":"Artificial Neural Nets and the Representation of Human Concepts","created":"2023-12-08","cited_by_count":3,"area":null},{"id":"2407.12200","title":"This Probably Looks Exactly Like That: An Invertible Prototypical Network","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2310.18496","title":"How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2411.03714","title":"Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative Measures","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2505.22199","title":"Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2105.02825","title":"Two4Two: Evaluating Interpretable Machine Learning - A Synthetic Dataset For Controlled Experiments","created":"2021-05-06","cited_by_count":1,"area":null},{"id":"2203.08312","title":"An explainability framework for cortical surface-based deep learning","created":"2022-03-15","cited_by_count":1,"area":null},{"id":"2211.00416","title":"Higher-order mutual information reveals synergistic sub-networks for multi-neuron importance","created":"2022-11-01","cited_by_count":1,"area":null},{"id":"2303.12032","title":"The Representational Status of Deep Learning Models","created":"2023-03-21","cited_by_count":1,"area":null},{"id":"2207.14160","title":"Do We Need Another Explainable AI Method? Toward Unifying Post-hoc XAI Evaluation Methods into an Interactive and Multi-dimensional Benchmark","created":"2022-06-08","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":"2401.14416","title":"Acoustic characterization of speech rhythm: going beyond metrics with recurrent neural networks","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2409.17157","title":"Confident Teacher, Confident Student? A Novel User Study Design for Investigating the Didactic Potential of Explanations and their Impact on Uncertainty","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2608.19168","title":"Learned, Then Lost: A Measured Single-Example Counterfactual in Pre-training","created":"2026-08-19","cited_by_count":0,"area":null}],"next_cursor":null}