{"total":21,"rows":[{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177,"area":null},{"id":"2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","created":"2024-05-30","cited_by_count":84,"area":null},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2407.15235","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","created":"2024-07-21","cited_by_count":30,"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":"2402.11192","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","created":"2024-02-17","cited_by_count":15,"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":"2412.00631","title":"ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning","created":"2024-12-01","cited_by_count":10,"area":null},{"id":"2410.04275","title":"Language Model-Driven Data Pruning Enables Efficient Active Learning","created":"2024-10-05","cited_by_count":6,"area":null},{"id":"2410.13464","title":"IterSelectTune: An Iterative Training Framework for Efficient Instruction-Tuning Data Selection","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2604.07892","title":"Data Selection for Multi-turn Dialogue Instruction Tuning","created":"2026-04-09","cited_by_count":4,"area":null},{"id":"2503.00034","title":"MergeIT: From Selection to Merging for Efficient Instruction Tuning","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2604.10448","title":"Instruction Data Selection via Answer Divergence","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2410.14853","title":"DFlow: Diverse Dialogue Flow Simulation with Large Language Models","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2502.11779","title":"Efficient Response Generation Strategy Selection for Fine-Tuning Large Language Models Through Self-Aligned Perplexity","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2503.04807","title":"Call for Rigor in Reporting Quality of Instruction Tuning Data","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2511.04406","title":"Dynamic Jointly Batch Selection for Data Efficient Machine Translation Fine-Tuning","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2604.11810","title":"GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.12944","title":"From Instance Selection to Fixed-Pool Data Recipe Search for Supervised Fine-Tuning","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2609.07183","title":"CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2411.14121","title":"Learning from \"Silly\" Questions Improves Large Language Models, But Only Slightly","created":"2024-11-21","cited_by_count":0,"area":null}],"next_cursor":null}