{"total":218,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2208.09399","title":"Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models","created":"2022-08-19","cited_by_count":198,"area":null},{"id":"2110.14049","title":"Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning","created":"2021-10-26","cited_by_count":165,"area":null},{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126,"area":null},{"id":"2107.07436","title":"FastSHAP: Real-Time Shapley Value Estimation","created":"2021-07-15","cited_by_count":125,"area":null},{"id":"2207.07605","title":"Algorithms to estimate Shapley value feature attributions","created":"2022-07-15","cited_by_count":115,"area":null},{"id":"2104.12199","title":"Sampling Permutations for Shapley Value Estimation","created":"2021-04-25","cited_by_count":102,"area":null},{"id":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102,"area":null},{"id":"2409.00729","title":"ContextCite: Attributing Model Generation to Context","created":"2024-09-01","cited_by_count":98,"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":"2209.04012","title":"From Shapley Values to Generalized Additive Models and back","created":"2022-09-08","cited_by_count":60,"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":"2301.00557","title":"Learning to Maximize Mutual Information for Dynamic Feature Selection","created":"2023-01-02","cited_by_count":56,"area":null},{"id":"2102.10936","title":"Shapley values for feature selection: The good, the bad, and the axioms","created":"2021-02-22","cited_by_count":54,"area":null},{"id":"2201.10295","title":"Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts","created":"2022-01-25","cited_by_count":53,"area":null},{"id":"2303.01179","title":"SHAP-IQ: Unified Approximation of any-order Shapley Interactions","created":"2023-03-02","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":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45,"area":null},{"id":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43,"area":null},{"id":"2410.01649","title":"shapiq: Shapley Interactions for Machine Learning","created":"2024-10-02","cited_by_count":43,"area":null},{"id":"2204.03972","title":"Contrastive language and vision learning of general fashion concepts","created":"2022-04-08","cited_by_count":42,"area":null},{"id":"2205.07277","title":"Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations","created":"2022-05-15","cited_by_count":40,"area":null},{"id":"2204.08945","title":"Missingness Bias in Model Debugging","created":"2022-04-19","cited_by_count":38,"area":null},{"id":"2304.07718","title":"Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value","created":"2023-04-16","cited_by_count":38,"area":null},{"id":"2105.00108","title":"Explaining a Series of Models by Propagating Shapley Values","created":"2021-04-30","cited_by_count":37,"area":null},{"id":"2306.05724","title":"Explaining Predictive Uncertainty with Information Theoretic Shapley Values","created":"2023-06-09","cited_by_count":36,"area":null},{"id":"2112.11407","title":"Toward Explainable AI for Regression Models","created":"2021-12-21","cited_by_count":31,"area":null},{"id":"2401.06654","title":"Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks","created":"2024-01-12","cited_by_count":28,"area":null},{"id":"2107.14317","title":"Temporal Dependencies in Feature Importance for Time Series Predictions","created":"2021-07-29","cited_by_count":27,"area":null},{"id":"2303.00652","title":"Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science","created":"2023-03-01","cited_by_count":27,"area":null},{"id":"2309.05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","created":"2023-09-12","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":"2303.05981","title":"Feature Importance: A Closer Look at Shapley Values and LOCO","created":"2023-03-10","cited_by_count":23,"area":null},{"id":"2405.10852","title":"KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactions","created":"2024-05-17","cited_by_count":22,"area":null},{"id":"2311.15722","title":"GLIME: General, Stable and Local LIME Explanation","created":"2023-11-27","cited_by_count":21,"area":null},{"id":"2401.15866","title":"Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution","created":"2024-01-29","cited_by_count":21,"area":null},{"id":"2111.13507","title":"Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features","created":"2021-11-26","cited_by_count":19,"area":null},{"id":"2305.15167","title":"Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models","created":"2023-05-24","cited_by_count":19,"area":null},{"id":"2306.07462","title":"On the Robustness of Removal-Based Feature Attributions","created":"2023-06-12","cited_by_count":19,"area":null},{"id":"2102.13519","title":"PredDiff: Explanations and Interactions from Conditional Expectations","created":"2021-02-26","cited_by_count":17,"area":null},{"id":"2204.11131","title":"Data Debugging with Shapley Importance over End-to-End Machine Learning Pipelines","created":"2022-04-23","cited_by_count":17,"area":null},{"id":"2304.01811","title":"HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation","created":"2023-04-04","cited_by_count":17,"area":null},{"id":"2312.01279","title":"TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents","created":"2023-12-03","cited_by_count":17,"area":"lr"},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2104.06164","title":"Fast Hierarchical Games for Image Explanations","created":"2021-04-13","cited_by_count":15,"area":null},{"id":"2305.09536","title":"A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Them","created":"2023-05-16","cited_by_count":15,"area":null},{"id":"2305.17043","title":"Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2504.12691","title":"Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2207.05566","title":"BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence","created":"2022-07-12","cited_by_count":13,"area":null},{"id":"2310.09925","title":"Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers","created":"2023-10-15","cited_by_count":13,"area":null},{"id":"2410.11087","title":"Locality Alignment Improves Vision-Language Models","created":"2024-10-14","cited_by_count":13,"area":"lr"},{"id":"2501.16944","title":"Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks","created":"2025-01-28","cited_by_count":13,"area":null},{"id":"2506.04202","title":"TracLLM: A Generic Framework for Attributing Long Context LLMs","created":"2025-06-04","cited_by_count":13,"area":null},{"id":"2302.12893","title":"Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluation","created":"2023-02-24","cited_by_count":11,"area":null},{"id":"2404.12862","title":"A Guide to Feature Importance Methods for Scientific Inference","created":"2024-04-19","cited_by_count":11,"area":null},{"id":"2106.02938","title":"Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning","created":"2021-06-05","cited_by_count":10,"area":null},{"id":"2308.14272","title":"Goodhart's Law Applies to NLP's Explanation Benchmarks","created":"2023-08-28","cited_by_count":10,"area":null},{"id":"2412.17152","title":"Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory","created":"2024-12-22","cited_by_count":10,"area":null},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2106.03820","title":"Accurate Shapley Values for explaining tree-based models","created":"2021-06-07","cited_by_count":9,"area":null},{"id":"2204.05044","title":"From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology","created":"2022-04-11","cited_by_count":9,"area":null},{"id":"2209.01939","title":"Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams","created":"2022-09-05","cited_by_count":9,"area":null},{"id":"2407.01300","title":"Collaborative Performance Prediction for Large Language Models","created":"2024-07-01","cited_by_count":9,"area":null},{"id":"2103.03302","title":"Ensembles of Random SHAPs","created":"2021-03-04","cited_by_count":8,"area":null},{"id":"2306.05500","title":"Word-Level Explanations for Analyzing Bias in Text-to-Image Models","created":"2023-06-03","cited_by_count":8,"area":null},{"id":"2306.12181","title":"Feature Interactions Reveal Linguistic Structure in Language Models","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2402.02870","title":"Rethinking Explainable Machine Learning as Applied Statistics","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2405.00708","title":"Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis","created":"2024-04-23","cited_by_count":8,"area":null},{"id":"2405.13536","title":"Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers","created":"2024-05-22","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":"2210.00107","title":"Contrastive Corpus Attribution for Explaining Representations","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2307.13582","title":"Argument Attribution Explanations in Quantitative Bipolar Argumentation Frameworks (Technical Report)","created":"2023-07-25","cited_by_count":7,"area":null},{"id":"2309.07593","title":"Statistically Valid Variable Importance Assessment through Conditional Permutations","created":"2023-09-14","cited_by_count":7,"area":null},{"id":"2309.07733","title":"Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features","created":"2023-09-14","cited_by_count":7,"area":null},{"id":"2310.12967","title":"Does Your Model Think Like an Engineer? Explainable AI for Bearing Fault Detection with Deep Learning","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2508.03793","title":"AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption","created":"2025-08-05","cited_by_count":7,"area":"rag"},{"id":"2601.18608","title":"PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression","created":"2026-01-26","cited_by_count":7,"area":null},{"id":"2106.09111","title":"An Imprecise SHAP as a Tool for Explaining the Class Probability Distributions under Limited Training Data","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2204.09938","title":"Ultra-marginal Feature Importance: Learning from Data with Causal Guarantees","created":"2022-04-21","cited_by_count":6,"area":null},{"id":"2205.13662","title":"Explaining Preferences with Shapley Values","created":"2022-05-26","cited_by_count":6,"area":null},{"id":"2205.13789","title":"A Sea of Words: An In-Depth Analysis of Anchors for Text Data","created":"2022-05-27","cited_by_count":6,"area":null},{"id":"2206.12481","title":"Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2207.07038","title":"SHAP-XRT: The Shapley Value Meets Conditional Independence Testing","created":"2022-07-14","cited_by_count":6,"area":null},{"id":"2210.17426","title":"Trade-off Between Efficiency and Consistency for Removal-based Explanations","created":"2022-10-31","cited_by_count":6,"area":null},{"id":"2306.05760","title":"Efficient GNN Explanation via Learning Removal-based Attribution","created":"2023-06-09","cited_by_count":6,"area":null},{"id":"2307.15361","title":"Confident Feature Ranking","created":"2023-07-28","cited_by_count":6,"area":null},{"id":"2310.12842","title":"Model-agnostic variable importance for predictive uncertainty: an entropy-based approach","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2311.07763","title":"The Disagreement Problem in Faithfulness Metrics","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2411.01710","title":"SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation","created":"2024-11-03","cited_by_count":6,"area":null},{"id":"2507.18043","title":"GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs","created":"2025-07-24","cited_by_count":6,"area":"mllm"},{"id":"2606.15390","title":"Not All Skills Help: Measuring and Repairing Agent Knowledge","created":"2026-06-13","cited_by_count":6,"area":"agents"},{"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":"2407.20990","title":"From Feature Importance to Natural Language Explanations Using LLMs with RAG","created":"2024-07-30","cited_by_count":5,"area":null},{"id":"2410.04883","title":"Improving the Weighting Strategy in KernelSHAP","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2505.07496","title":"DocVXQA: Context-Aware Visual Explanations for Document Question Answering","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2505.13118","title":"Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2203.06043","title":"Sparse Subspace Clustering for Concept Discovery (SSCCD)","created":"2022-03-11","cited_by_count":4,"area":null},{"id":"2203.07861","title":"Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Series","created":"2022-03-14","cited_by_count":4,"area":null},{"id":"2305.19998","title":"Efficient Shapley Values Estimation by Amortization for Text Classification","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2311.13061","title":"Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue","created":"2023-11-21","cited_by_count":4,"area":null}],"next_cursor":"100"}