{"total":18,"rows":[{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2503.01807","title":"Large-Scale Data Selection for Instruction Tuning","created":"2025-03-03","cited_by_count":35,"area":null},{"id":"2507.09424","title":"DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models","created":"2025-07-12","cited_by_count":5,"area":null},{"id":"2508.04329","title":"Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2605.15675","title":"Interaction-Aware Influence Functions for Group Attribution","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2505.21438","title":"Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2507.12612","title":"Learning Task Mixtures from Task Affinities: A Probabilistic Graphical Model for Supervised Fine-Tuning","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2605.15691","title":"SEED: Targeted Data Selection by Weighted Independent Set","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.21422","title":"PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2609.19589","title":"Form Over Content In Gradient-Based Data Attribution Methods","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2605.16704","title":"Convex Dataset Valuation for Post-Training","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.30857","title":"MADS: Model-Aware Diverse Core Set Selection for Instruction Tuning","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.10706","title":"Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.29118","title":"Emergent Misalignment Is Not Magical","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.31214","title":"Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32888","title":"Refreshing Less, Selecting Better: Reusing Stale Gradient Features for Efficient Influence-Based Data Selection","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.12345","title":"Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.16531","title":"Support or Magnitude? Characterizing Neuron Relevance for Instruction Data Selection","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}