{"total":18,"rows":[{"id":"2502.17184","title":"Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric","created":"2025-02-24","cited_by_count":24,"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":"2504.17119","title":"The Rise of Small Language Models in Healthcare: A Comprehensive Survey","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2410.15225","title":"Chasing Random: Instruction Selection Strategies Fail to Generalize","created":"2024-10-19","cited_by_count":13,"area":null},{"id":"2511.07074","title":"Importance-Aware Data Selection for Efficient LLM Instruction Tuning","created":"2025-11-10","cited_by_count":7,"area":null},{"id":"2409.14673","title":"Instruction Tuning Vs. In-Context Learning: Revisiting Large Language Models in Few-Shot Computational Social Science","created":"2024-09-23","cited_by_count":5,"area":null},{"id":"2408.11852","title":"Fast Training Dataset Attribution via In-Context Learning","created":"2024-08-14","cited_by_count":2,"area":null},{"id":"2602.11089","title":"DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2503.13383","title":"Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2507.21482","title":"Improving Task Diversity in Label Efficient Supervised Finetuning of LLMs","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2603.13201","title":"Neuron-Aware Data Selection In Instruction Tuning For Large Language Models","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2604.00001","title":"Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2607.18960","title":"SFGA: A Statistics-First Gating Architecture with Adjudicative Escalation for Trustworthy SFT Data Procurement","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2502.11419","title":"InsBank: Evolving Instruction Subset for Ongoing Alignment","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2503.15924","title":"Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2506.21564","title":"Team QUST at SemEval-2025 Task 10: Evaluating Large Language Models in Multiclass Multi-label Classification of News Entity Framing","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2509.06463","title":"Accelerate Scaling of LLM Finetuning via Quantifying the Coverage and Depth of Instruction Set","created":"2025-09-08","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}],"next_cursor":null}