{"total":21,"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":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105,"area":null},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81,"area":null},{"id":"2409.18153","title":"Most Influential Subset Selection: Challenges, Promises, and Beyond","created":"2024-09-25","cited_by_count":32,"area":null},{"id":"2405.03875","title":"Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits","created":"2024-05-06","cited_by_count":29,"area":null},{"id":"2504.16430","title":"MAGIC: Near-Optimal Data Attribution for Deep Learning","created":"2025-04-23","cited_by_count":22,"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":"2303.14582","title":"Identification of Negative Transfers in Multitask Learning Using Surrogate Models","created":"2023-03-25","cited_by_count":20,"area":null},{"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":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2410.23808","title":"One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2502.00270","title":"DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks","created":"2025-02-01","cited_by_count":6,"area":null},{"id":"2304.10701","title":"GMValuator: Similarity-based Data Valuation for Generative Models","created":"2023-04-21","cited_by_count":5,"area":null},{"id":"2310.17044","title":"Learning to Rank for Active Learning via Multi-Task Bilevel Optimization","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2604.07328","title":"How to sketch a learning algorithm","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2605.15675","title":"Interaction-Aware Influence Functions for Group Attribution","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2211.09752","title":"Learning to Counterfactually Explain Recommendations","created":"2022-11-17","cited_by_count":1,"area":null},{"id":"2505.16260","title":"Small-to-Large Generalization: Data Influences Models Consistently Across Scale","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2508.10866","title":"Efficiently Verifiable Proofs of Data Attribution","created":"2025-08-14","cited_by_count":1,"area":null}],"next_cursor":null}