{"total":55,"rows":[{"id":"2402.05123","title":"A Survey on Data Selection for LLM Instruction Tuning","created":"2024-02-04","cited_by_count":77,"area":null},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2402.16705","title":"SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection","created":"2024-02-26","cited_by_count":34,"area":null},{"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":"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":"2503.11441","title":"D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning","created":"2025-03-14","cited_by_count":21,"area":null},{"id":"2405.00705","title":"SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning","created":"2024-04-23","cited_by_count":19,"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":"2402.11138","title":"Contrastive Instruction Tuning","created":"2024-02-17","cited_by_count":17,"area":null},{"id":"2401.16553","title":"SelectLLM: Can LLMs Select Important Instructions to Annotate?","created":"2024-01-29","cited_by_count":16,"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":"2505.20903","title":"Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?","created":"2025-05-27","cited_by_count":11,"area":null},{"id":"2404.16766","title":"Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model","created":"2024-04-25","cited_by_count":10,"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":"2402.16058","title":"Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression","created":"2024-02-25","cited_by_count":8,"area":null},{"id":"2409.03810","title":"How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2410.14745","title":"Semi-supervised Fine-tuning for Large Language Models","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2505.09503","title":"Towards Fair In-Context Learning with Tabular Foundation Models","created":"2025-05-14","cited_by_count":8,"area":null},{"id":"2606.23127","title":"Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation","created":"2026-06-22","cited_by_count":8,"area":"agents"},{"id":"2312.15692","title":"Instruction Fusion: Advancing Prompt Evolution through Hybridization","created":"2023-12-25","cited_by_count":7,"area":null},{"id":"2403.02586","title":"Improving Event Definition Following For Zero-Shot Event Detection","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2508.21589","title":"Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning","created":"2025-08-29","cited_by_count":7,"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":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2406.04638","title":"Large Language Model-guided Document Selection","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2412.14809","title":"ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis","created":"2024-12-19","cited_by_count":4,"area":"synth"},{"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":"2511.08263","title":"ImagebindDC: Compressing Multi-modal Data with Imagebind-based Condensation","created":"2025-11-11","cited_by_count":4,"area":null},{"id":"2408.12799","title":"Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora","created":"2024-08-23","cited_by_count":3,"area":"alignment"},{"id":"2410.05248","title":"SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2504.07288","title":"MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning","created":"2025-04-09","cited_by_count":3,"area":null},{"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":"2412.15652","title":"Error-driven Data-efficient Large Multimodal Model Tuning","created":"2024-12-20","cited_by_count":2,"area":"mllm"},{"id":"2506.10288","title":"ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2509.20321","title":"Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2510.16806","title":"Computational Budget Should Be Considered in Data Selection","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2605.03514","title":"Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2409.08474","title":"Rethinking Meta-Learning from a Learning Lens","created":"2024-09-13","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":"2508.07638","title":"Data Selection for LLM Alignment Using Fine-Grained Preferences","created":"2025-08-11","cited_by_count":1,"area":"alignment"},{"id":"2608.00181","title":"Cross-Benchmark Generalization in Long-Horizon Agents","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2402.03049","title":"EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2404.08846","title":"Experimental Design for Active Transductive Inference in Large Language Models","created":"2024-04-12","cited_by_count":0,"area":null},{"id":"2408.02861","title":"A Framework for Fine-Tuning LLMs using Heterogeneous Feedback","created":"2024-08-05","cited_by_count":0,"area":"alignment"},{"id":"2410.02795","title":"TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolution","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2507.03673","title":"TACOS: Open Tagging and Comparative Scoring for Instruction Fine-Tuning Data Selection","created":"2025-07-04","cited_by_count":0,"area":"alignment"},{"id":"2507.23543","title":"ART: Adaptive Relation Tuning for Generalized Relation Prediction","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2509.15549","title":"M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2510.24425","title":"Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models","created":"2025-10-28","cited_by_count":0,"area":"distill"},{"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":"2606.07690","title":"HARP: Efficient Data Selection for Finetuning Large Language Models","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2610.02593","title":"Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models","created":"2026-10-01","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}