{"total":76,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"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":"2402.00530","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","created":"2024-02-01","cited_by_count":138,"area":null},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"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":"2402.02318","title":"Diversity Measurement and Subset Selection for Instruction Tuning Datasets","created":"2024-02-04","cited_by_count":29,"area":null},{"id":"2402.08259","title":"A Survey of Table Reasoning with Large Language Models","created":"2024-02-13","cited_by_count":29,"area":"lr"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2501.00654","title":"ICONS: Influence Consensus for Vision-Language Data Selection","created":"2024-12-31","cited_by_count":29,"area":"mllm"},{"id":"2412.08819","title":"HARP: A challenging human-annotated math reasoning benchmark","created":"2024-12-11","cited_by_count":27,"area":"lr"},{"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":"2401.06692","title":"An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models","created":"2024-01-12","cited_by_count":23,"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":"2505.12212","title":"Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning","created":"2025-05-18","cited_by_count":20,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2402.10891","title":"Instruction Diversity Drives Generalization To Unseen Tasks","created":"2024-02-16","cited_by_count":16,"area":null},{"id":"2408.02193","title":"CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMs","created":"2024-08-05","cited_by_count":15,"area":null},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2411.04425","title":"DELIFT: Data Efficient Language model Instruction Fine Tuning","created":"2024-11-07","cited_by_count":14,"area":null},{"id":"2409.11378","title":"Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement","created":"2024-09-17","cited_by_count":13,"area":null},{"id":"2505.07437","title":"LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning","created":"2025-05-12","cited_by_count":13,"area":"alignment"},{"id":"2407.19580","title":"Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures","created":"2024-07-28","cited_by_count":12,"area":null},{"id":"2502.14050","title":"Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder","created":"2025-02-19","cited_by_count":12,"area":"mechinterp"},{"id":"2504.13835","title":"MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space","created":"2025-04-18","cited_by_count":12,"area":null},{"id":"2503.00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","created":"2025-03-02","cited_by_count":11,"area":null},{"id":"2405.13326","title":"Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning","created":"2024-05-22","cited_by_count":9,"area":"synth"},{"id":"2410.14745","title":"Semi-supervised Fine-tuning for Large Language Models","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2504.07749","title":"NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark","created":"2025-04-10","cited_by_count":8,"area":null},{"id":"2408.14960","title":"Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2503.17195","title":"TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2505.17266","title":"Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2510.01454","title":"Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories","created":"2025-10-01","cited_by_count":7,"area":"mllm"},{"id":"2511.07074","title":"Importance-Aware Data Selection for Efficient LLM Instruction Tuning","created":"2025-11-10","cited_by_count":7,"area":null},{"id":"2406.10882","title":"SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models","created":"2024-06-16","cited_by_count":6,"area":null},{"id":"2503.01836","title":"CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom","created":"2025-03-03","cited_by_count":6,"area":"synth"},{"id":"2603.06745","title":"Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection","created":"2026-03-06","cited_by_count":6,"area":"mechinterp"},{"id":"2504.12687","title":"Data-efficient LLM Fine-tuning for Code Generation","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2502.12494","title":"EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness","created":"2025-02-18","cited_by_count":4,"area":"agents"},{"id":"2505.22076","title":"ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2510.09426","title":"KORMo: Korean Open Reasoning Model for Everyone","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2505.05327","title":"RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2505.24768","title":"From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning","created":"2025-05-30","cited_by_count":3,"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":"2605.05227","title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods","created":"2026-04-19","cited_by_count":3,"area":"lr"},{"id":"2505.20264","title":"We Need to Measure Data Diversity in NLP -- Better and Broader","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2509.22480","title":"Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2512.06678","title":"GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2607.09739","title":"Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2608.24065","title":"Mechanistic Circuit Identification for Controllable Data Generation","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2403.19822","title":"Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2505.22157","title":"LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy","created":"2025-05-28","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":"2510.14459","title":"Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning","created":"2025-10-16","cited_by_count":1,"area":"alignment"},{"id":"2510.21885","title":"Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2602.13773","title":"On Representation Redundancy in Large-Scale Instruction Tuning Data Selection","created":"2026-02-14","cited_by_count":1,"area":null},{"id":"2603.13790","title":"Aligning the Query Space: Greedy Information Projection for Language Model Data Selection","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2603.16878","title":"A foundation model for electrodermal activity data","created":"2026-02-20","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":"2606.07678","title":"DOG-DPO:Dynamic Optimization in Geometry for Safety Alignment","created":"2026-06-04","cited_by_count":1,"area":"alignment"},{"id":"2607.19848","title":"emb-diversity: A Tool for Embedding-Based Measurement of Data Diversity","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2507.15092","title":"A Penalty Goes a Long Way: Measuring Lexical Diversity in Synthetic Texts Under Prompt-Influenced Length Variations","created":"2025-07-20","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":"2510.13624","title":"Unlocking Public Catalogues: Instruction-Tuning LLMs for ICD Coding of German Tumor Diagnoses","created":"2025-10-15","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":"2601.13995","title":"From Tags to Trees: Structuring Fine-Grained Knowledge for Controllable Data Selection in LLM Instruction Tuning","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2604.25167","title":"From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models","created":"2026-04-28","cited_by_count":0,"area":"mechinterp"},{"id":"2605.15012","title":"Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.20291","title":"Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection","created":"2026-05-19","cited_by_count":0,"area":"agents"},{"id":"2606.07690","title":"HARP: Efficient Data Selection for Finetuning Large Language Models","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2607.06160","title":"LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction Synthesis","created":"2026-07-07","cited_by_count":0,"area":"synth"},{"id":"2608.17379","title":"PTXBench: Benchmarking and Adapting LLMs for GPU Kernel Optimization with Architecture-specific PTX","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.32484","title":"Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling","created":"2026-09-26","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":"2609.34205","title":"Learning to Optimize through Solver-Grounded Self-Play","created":"2026-09-28","cited_by_count":0,"area":"synth"},{"id":"2609.36721","title":"CALIBUDGET: Calibration-Guided Source Allocation for Fixed-Budget Mixed-Reasoning Adaptation","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}