{"total":21,"rows":[{"id":"2502.01968","title":"Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning","created":"2025-02-04","cited_by_count":39,"area":null},{"id":"2501.12147","title":"Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities","created":"2025-01-21","cited_by_count":23,"area":null},{"id":"2505.19051","title":"Efficient Data Selection at Scale via Influence Distillation","created":"2025-05-25","cited_by_count":15,"area":null},{"id":"2506.01317","title":"T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2510.25817","title":"A Survey on Efficient Large Language Model Training: From Data-centric Perspectives","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2510.02330","title":"EntropyLong: Effective Long-Context Training via Predictive Uncertainty","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2510.18250","title":"ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2506.06991","title":"Evaluating LLM-Contaminated Crowdsourcing Data Without Ground Truth","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2511.07198","title":"Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2606.18286","title":"CODEBLOCK: Learning to Supervise Code at the Right Granularity","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2506.16731","title":"Incentivizing High-quality Participation From Federated Learning Agents","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2512.12072","title":"VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2602.01161","title":"The Role of Dataset Linguistic Structure in the Cultural Awareness of Large Language Models","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2603.12478","title":"Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.29807","title":"Data filtering methods for training language models","created":"2026-05-28","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":"2607.29283","title":"RTLCurator: Label-Efficient Data Curation for RTL Generation","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2610.06387","title":"Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.13386","title":"MoPrO-SD: Modular Prompt Optimization for Stance Detection","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17158","title":"The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}