{"total":144,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"area":"safety"},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123,"area":"diffusion"},{"id":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","cited_by_count":96,"area":"safety"},{"id":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94,"area":null},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87,"area":null},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81,"area":null},{"id":"2310.12560","title":"Fast Model Debias with Machine Unlearning","created":"2023-10-19","cited_by_count":72,"area":"safety"},{"id":"2406.09073","title":"Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition","created":"2024-06-13","cited_by_count":50,"area":"safety"},{"id":"2302.06755","title":"Dataset Distillation with Convexified Implicit Gradients","created":"2023-02-13","cited_by_count":46,"area":null},{"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":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34,"area":null},{"id":"2409.16986","title":"Harnessing Diversity for Important Data Selection in Pretraining Large Language Models","created":"2024-09-25","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":"2305.16971","title":"Theoretical and Practical Perspectives on what Influence Functions Do","created":"2023-05-26","cited_by_count":29,"area":null},{"id":"2405.20272","title":"Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable","created":"2024-05-30","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":"2411.15102","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","created":"2024-11-22","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":"2307.02185","title":"Citation: A Key to Building Responsible and Accountable Large Language Models","created":"2023-07-05","cited_by_count":20,"area":null},{"id":"2405.11724","title":"Token-wise Influential Training Data Retrieval for Large Language Models","created":"2024-05-20","cited_by_count":20,"area":null},{"id":"2406.04327","title":"Causal Estimation of Memorisation Profiles","created":"2024-06-06","cited_by_count":20,"area":null},{"id":"2409.19998","title":"Do Influence Functions Work on Large Language Models?","created":"2024-09-30","cited_by_count":20,"area":null},{"id":"2212.03905","title":"Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve","created":"2022-12-07","cited_by_count":18,"area":null},{"id":"2410.04555","title":"$\\texttt{dattri}$: A Library for Efficient Data Attribution","created":"2024-10-06","cited_by_count":18,"area":null},{"id":"2410.03249","title":"How Much Can We Forget about Data Contamination?","created":"2024-10-04","cited_by_count":14,"area":null},{"id":"2309.03234","title":"Natural Example-Based Explainability: a Survey","created":"2023-09-05","cited_by_count":13,"area":null},{"id":"2402.15109","title":"Remaining-data-free Machine Unlearning by Suppressing Sample Contribution","created":"2024-02-23","cited_by_count":13,"area":"safety"},{"id":"2410.14208","title":"Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning","created":"2024-10-18","cited_by_count":13,"area":null},{"id":"2305.19765","title":"A Bayesian Approach To Analysing Training Data Attribution In Deep Learning","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","cited_by_count":11,"area":"safety"},{"id":"2311.12233","title":"Unifying Corroborative and Contributive Attributions in Large Language Models","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2402.18726","title":"Unveiling Privacy, Memorization, and Input Curvature Links","created":"2024-02-28","cited_by_count":10,"area":null},{"id":"2409.17357","title":"Revisiting inverse Hessian vector products for calculating influence functions","created":"2024-09-25","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":"2312.05705","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2505.18513","title":"Enhancing Training Data Attribution with Representational Optimization","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2302.03519","title":"Efficient Parametric Approximations of Neural Network Function Space Distance","created":"2023-02-07","cited_by_count":7,"area":null},{"id":"2303.01928","title":"Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Values","created":"2023-03-03","cited_by_count":7,"area":null},{"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":"2410.01285","title":"Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2510.12071","title":"Influence Dynamics and Stagewise Data Attribution","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2309.13016","title":"Understanding Deep Gradient Leakage via Inversion Influence Functions","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2312.02438","title":"Adaptive Instrument Design for Indirect Experiments","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2402.12118","title":"Sparse, Efficient and Explainable Data Attribution with DualXDA","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2502.19770","title":"TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning","created":"2025-02-27","cited_by_count":6,"area":"safety"},{"id":"2503.07315","title":"Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2507.15836","title":"Optimizing Canaries for Privacy Auditing with Metagradient Descent","created":"2025-07-21","cited_by_count":6,"area":"safety"},{"id":"2304.10701","title":"GMValuator: Similarity-based Data Valuation for Generative Models","created":"2023-04-21","cited_by_count":5,"area":null},{"id":"2308.14412","title":"Task-Aware Machine Unlearning and Its Application in Load Forecasting","created":"2023-08-28","cited_by_count":5,"area":null},{"id":"2405.17293","title":"Efficient Ensembles Improve Training Data Attribution","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2406.16846","title":"Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection","created":"2024-06-24","cited_by_count":5,"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":"2602.09987","title":"Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions","created":"2026-02-10","cited_by_count":5,"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":"2403.00158","title":"Automated Efficient Estimation using Monte Carlo Efficient Influence Functions","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2505.19097","title":"Towards Robust Influence Functions with Flat Validation Minima","created":"2025-05-25","cited_by_count":4,"area":null},{"id":"2505.22601","title":"Machine Unlearning under Overparameterization","created":"2025-05-28","cited_by_count":4,"area":"safety"},{"id":"2506.06656","title":"Rescaled Influence Functions: Accurate Data Attribution in High Dimension","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2510.02334","title":"Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing","created":"2025-09-26","cited_by_count":4,"area":"safety"},{"id":"2601.10645","title":"Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMs","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2602.10568","title":"Gauss-Newton Unlearning for the LLM Era","created":"2026-02-11","cited_by_count":4,"area":"safety"},{"id":"2605.18814","title":"How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2403.15576","title":"Data-centric Prediction Explanation via Kernelized Stein Discrepancy","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2403.19381","title":"On Uncertainty Quantification for Near-Bayes Optimal Algorithms","created":"2024-03-28","cited_by_count":3,"area":null},{"id":"2404.14006","title":"Distilled Datamodel with Reverse Gradient Matching","created":"2024-04-22","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":"2505.20076","title":"ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior","created":"2025-05-26","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":"2601.21929","title":"LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2305.18818","title":"Shapley Based Residual Decomposition for Instance Analysis","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2310.04649","title":"Uncovering Model Processing Strategies with Non-Negative Per-Example Fisher Factorization","created":"2023-10-07","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":"2408.10468","title":"Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2409.05208","title":"Influence-based Attributions can be Manipulated","created":"2024-09-08","cited_by_count":2,"area":null},{"id":"2506.10946","title":"GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models","created":"2025-06-12","cited_by_count":2,"area":"safety"},{"id":"2507.11895","title":"Newfluence: Boosting Model interpretability and Understanding in High Dimensions","created":"2025-07-16","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":"2510.24884","title":"Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2601.02386","title":"Tree of Preferences for Diversified Recommendation","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2604.08423","title":"Synthetic Data for any Differentiable Target","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2605.15675","title":"Interaction-Aware Influence Functions for Group Attribution","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.15761","title":"A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2607.00510","title":"Prototype Language Models","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2305.20002","title":"Representer Point Selection for Explaining Regularized High-dimensional Models","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2309.08678","title":"Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2311.03075","title":"SoK: Memorisation in machine learning","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2406.02745","title":"Measuring Stochastic Data Complexity with Boltzmann Influence Functions","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2407.14859","title":"Enhancing High-Energy Particle Physics Collision Analysis through Graph Data Attribution Techniques","created":"2024-07-20","cited_by_count":1,"area":null}],"next_cursor":"100"}