{"total":147,"rows":[{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2310.10683","title":"Large Language Model Unlearning","created":"2023-10-14","cited_by_count":302,"area":"safety"},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"id":"2108.11577","title":"Machine Unlearning of Features and Labels","created":"2021-08-26","cited_by_count":229,"area":"safety"},{"id":"2111.08947","title":"Fast Yet Effective Machine Unlearning","created":"2021-11-17","cited_by_count":217,"area":"safety"},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156,"area":null},{"id":"2209.05364","title":"If Influence Functions are the Answer, Then What is the Question?","created":"2022-09-12","cited_by_count":144,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","created":"2022-05-19","cited_by_count":133,"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":"2302.11042","title":"In-context Example Selection with Influences","created":"2023-02-21","cited_by_count":61,"area":null},{"id":"2303.08114","title":"Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs","created":"2023-03-14","cited_by_count":53,"area":null},{"id":"2206.10013","title":"Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments","created":"2022-06-20","cited_by_count":50,"area":null},{"id":"2106.03922","title":"Interactive Label Cleaning with Example-based Explanations","created":"2021-06-07","cited_by_count":49,"area":null},{"id":"2311.00500","title":"Intriguing Properties of Data Attribution on Diffusion Models","created":"2023-11-01","cited_by_count":47,"area":"diffusion"},{"id":"2312.06205","title":"The Journey, Not the Destination: How Data Guides Diffusion Models","created":"2023-12-11","cited_by_count":43,"area":"diffusion"},{"id":"2102.02515","title":"HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks","created":"2021-02-04","cited_by_count":38,"area":null},{"id":"2202.00787","title":"Achieving Fairness at No Utility Cost via Data Reweighing with Influence","created":"2022-02-01","cited_by_count":38,"area":null},{"id":"2404.15381","title":"Advances and Open Challenges in Federated Foundation Models","created":"2024-04-23","cited_by_count":36,"area":null},{"id":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2410.13850","title":"Influence Functions for Scalable Data Attribution in Diffusion Models","created":"2024-10-17","cited_by_count":33,"area":"diffusion"},{"id":"2409.18153","title":"Most Influential Subset Selection: Challenges, Promises, and Beyond","created":"2024-09-25","cited_by_count":32,"area":null},{"id":"2203.11491","title":"Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation","created":"2022-03-22","cited_by_count":29,"area":"safety"},{"id":"2305.16971","title":"Theoretical and Practical Perspectives on what Influence Functions Do","created":"2023-05-26","cited_by_count":29,"area":null},{"id":"2202.05189","title":"Understanding Rare Spurious Correlations in Neural Networks","created":"2022-02-10","cited_by_count":27,"area":null},{"id":"2207.04806","title":"Repairing Neural Networks by Leaving the Right Past Behind","created":"2022-07-11","cited_by_count":27,"area":null},{"id":"2112.08297","title":"Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime","created":"2021-12-15","cited_by_count":26,"area":null},{"id":"2202.13585","title":"Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten","created":"2022-02-28","cited_by_count":25,"area":"safety"},{"id":"2210.01072","title":"Understanding Influence Functions and Datamodels via Harmonic Analysis","created":"2022-10-03","cited_by_count":23,"area":null},{"id":"2506.19121","title":"CUPID: Curating Data your Robot Loves with Influence Functions","created":"2025-06-23","cited_by_count":23,"area":"offlinerl"},{"id":"2504.16430","title":"MAGIC: Near-Optimal Data Attribution for Deep Learning","created":"2025-04-23","cited_by_count":22,"area":null},{"id":"2105.14203","title":"Understanding Instance-based Interpretability of Variational Auto-Encoders","created":"2021-05-29","cited_by_count":21,"area":null},{"id":"2304.10177","title":"Regularizing Second-Order Influences for Continual Learning","created":"2023-04-20","cited_by_count":21,"area":null},{"id":"2410.11215","title":"A CLIP-Powered Framework for Robust and Generalizable Data Selection","created":"2024-10-15","cited_by_count":21,"area":null},{"id":"2303.12922","title":"Revisiting the Fragility of Influence Functions","created":"2023-03-22","cited_by_count":20,"area":null},{"id":"2309.17310","title":"Leave-one-out Distinguishability in Machine Learning","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2401.15241","title":"Unlearning Traces the Influential Training Data of Language Models","created":"2024-01-26","cited_by_count":18,"area":"safety"},{"id":"2101.09648","title":"Leveraging Expert Consistency to Improve Algorithmic Decision Support","created":"2021-01-24","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":"2111.03120","title":"Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods","created":"2021-11-04","cited_by_count":16,"area":"safety"},{"id":"2210.07441","title":"Characterizing the Influence of Graph Elements","created":"2022-10-14","cited_by_count":16,"area":null},{"id":"2310.19273","title":"The Memory Perturbation Equation: Understanding Model's Sensitivity to Data","created":"2023-10-30","cited_by_count":16,"area":null},{"id":"2310.05847","title":"Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems","created":"2023-10-06","cited_by_count":15,"area":"safety"},{"id":"2309.03234","title":"Natural Example-Based Explainability: a Survey","created":"2023-09-05","cited_by_count":13,"area":null},{"id":"2502.14709","title":"Group-Level Data Selection for Efficient Pretraining","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2106.04753","title":"On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation","created":"2021-06-09","cited_by_count":12,"area":null},{"id":"2201.05759","title":"FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes","created":"2022-01-15","cited_by_count":12,"area":null},{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2101.08521","title":"Out-of-Distribution Generalization Analysis via Influence Function","created":"2021-01-21","cited_by_count":11,"area":null},{"id":"2202.01315","title":"Approximating Full Conformal Prediction at Scale via Influence Functions","created":"2022-02-02","cited_by_count":11,"area":null},{"id":"2302.13473","title":"Towards Interpretable Federated Learning","created":"2023-02-27","cited_by_count":11,"area":null},{"id":"2110.12122","title":"Quantifying Epistemic Uncertainty in Deep Learning","created":"2021-10-23","cited_by_count":10,"area":null},{"id":"2302.02169","title":"How Many and Which Training Points Would Need to be Removed to Flip this Prediction?","created":"2023-02-04","cited_by_count":10,"area":null},{"id":"2306.05674","title":"Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks","created":"2023-06-09","cited_by_count":10,"area":null},{"id":"2311.12233","title":"Unifying Corroborative and Contributive Attributions in Large Language Models","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2212.00261","title":"Task Discovery: Finding the Tasks that Neural Networks Generalize on","created":"2022-12-01","cited_by_count":9,"area":null},{"id":"2406.07698","title":"Label Smoothing Improves Machine Unlearning","created":"2024-06-11","cited_by_count":9,"area":"safety"},{"id":"2408.03560","title":"In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models","created":"2024-08-07","cited_by_count":9,"area":null},{"id":"2205.12879","title":"Understanding Programmatic Weak Supervision via Source-aware Influence Function","created":"2022-05-25","cited_by_count":8,"area":null},{"id":"2310.05331","title":"Unlearning with Fisher Masking","created":"2023-10-09","cited_by_count":8,"area":"safety"},{"id":"2505.18513","title":"Enhancing Training Data Attribution with Representational Optimization","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2602.14869","title":"Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution","created":"2026-02-16","cited_by_count":8,"area":"mechinterp"},{"id":"2312.05586","title":"Deeper Understanding of Black-box Predictions via Generalized Influence Functions","created":"2023-12-09","cited_by_count":7,"area":null},{"id":"2410.16710","title":"Influential Language Data Selection via Gradient Trajectory Pursuit","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2412.12836","title":"A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions","created":"2024-12-17","cited_by_count":7,"area":null},{"id":"2205.14284","title":"Provably Auditing Ordinary Least Squares in Low Dimensions","created":"2022-05-28","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":"2307.15960","title":"Recommendation Unlearning via Matrix Correction","created":"2023-07-29","cited_by_count":6,"area":null},{"id":"2310.00840","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2407.15247","title":"TimeInf: Time Series Data Contribution via Influence Functions","created":"2024-07-21","cited_by_count":6,"area":null},{"id":"2410.09940","title":"Generalized Group Data Attribution","created":"2024-10-13","cited_by_count":6,"area":null},{"id":"2412.03906","title":"Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2510.10161","title":"Large Language Model Sourcing: A Survey","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2107.05978","title":"DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement","created":"2021-07-13","cited_by_count":4,"area":null},{"id":"2206.14439","title":"Approximate Data Deletion in Generative Models","created":"2022-06-29","cited_by_count":4,"area":null},{"id":"2310.07882","title":"The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2407.03153","title":"An Efficient Framework for Crediting Data Contributors of Diffusion Models","created":"2024-06-09","cited_by_count":4,"area":"diffusion"},{"id":"2505.24261","title":"Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2506.06656","title":"Rescaled Influence Functions: Accurate Data Attribution in High Dimension","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2506.21910","title":"AutoMixer: Checkpoint Artifacts as Automatic Data Mixers","created":"2025-06-27","cited_by_count":4,"area":null},{"id":"2305.12809","title":"Relabeling Minimal Training Subset to Flip a Prediction","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2310.20477","title":"Exploring Practitioner Perspectives On Training Data Attribution Explanations","created":"2023-10-31","cited_by_count":3,"area":null},{"id":"2409.16978","title":"Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2506.04694","title":"Influence Functions for Edge Edits in Non-Convex Graph Neural Networks","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2506.12965","title":"Distributional Training Data Attribution: What do Influence Functions Sample?","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2508.14648","title":"Understanding Data Influence with Differential Approximation","created":"2025-08-20","cited_by_count":3,"area":null},{"id":"2509.23437","title":"Better Hessians Matter: Studying the Impact of Curvature Approximations in Influence Functions","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2104.13230","title":"Influence Based Defense Against Data Poisoning Attacks in Online Learning","created":"2021-04-24","cited_by_count":2,"area":"safety"},{"id":"2109.06999","title":"Behavior of k-NN as an Instance-Based Explanation Method","created":"2021-09-14","cited_by_count":2,"area":null},{"id":"2111.12545","title":"ModelPred: A Framework for Predicting Trained Model from Training Data","created":"2021-11-24","cited_by_count":2,"area":null},{"id":"2209.13858","title":"Variance Tolerance Factors For Interpreting ALL Neural Networks","created":"2022-09-28","cited_by_count":2,"area":null},{"id":"2403.00315","title":"Axe the X in XAI: A Plea for Understandable AI","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2407.08169","title":"The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2410.05675","title":"Understanding with toy surrogate models in machine learning","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2502.16152","title":"DUPRE: Data Utility Prediction for Efficient Data Valuation","created":"2025-02-22","cited_by_count":2,"area":null},{"id":"2509.15651","title":"Toward Efficient Influence Function: Dropout as a Compression Tool","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2510.20372","title":"Testing Most Influential Sets","created":"2025-10-23","cited_by_count":2,"area":null}],"next_cursor":"100"}