{"total":107,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2409.00920","title":"ToolACE: Winning the Points of LLM Function Calling","created":"2024-09-02","cited_by_count":216,"area":"agents"},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209,"area":"mllm"},{"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":"2404.01099","title":"What is in Your Safe Data? Identifying Benign Data that Breaks Safety","created":"2024-04-01","cited_by_count":118,"area":"safety"},{"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":"2505.22375","title":"Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition","created":"2025-05-28","cited_by_count":62,"area":"lr"},{"id":"2407.03104","title":"KeyVideoLLM: Towards Large-scale Video Keyframe Selection","created":"2024-07-03","cited_by_count":54,"area":null},{"id":"2402.18191","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","created":"2024-02-28","cited_by_count":53,"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":"2407.01085","title":"Explaining Length Bias in LLM-Based Preference Evaluations","created":"2024-07-01","cited_by_count":49,"area":null},{"id":"2407.06645","title":"Entropy Law: The Story Behind Data Compression and LLM Performance","created":"2024-07-09","cited_by_count":44,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2502.09650","title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples","created":"2025-02-11","cited_by_count":37,"area":"alignment"},{"id":"2503.01807","title":"Large-Scale Data Selection for Instruction Tuning","created":"2025-03-03","cited_by_count":35,"area":null},{"id":"2312.11508","title":"Rethinking the Instruction Quality: LIFT is What You Need","created":"2023-12-12","cited_by_count":34,"area":"lr"},{"id":"2601.16725","title":"LongCat-Flash-Thinking-2601 Technical Report","created":"2026-01-23","cited_by_count":34,"area":"lr"},{"id":"2405.12915","title":"G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translation","created":"2024-05-21","cited_by_count":30,"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":"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":"2408.08072","title":"I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm","created":"2024-08-15","cited_by_count":27,"area":null},{"id":"2407.10627","title":"Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena","created":"2024-07-15","cited_by_count":26,"area":null},{"id":"2406.10995","title":"Concept-skill Transferability-based Data Selection for Large Vision-Language Models","created":"2024-06-16","cited_by_count":24,"area":"mllm"},{"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":"2502.17514","title":"SAE-V: Interpreting Multimodal Models for Enhanced Alignment","created":"2025-02-22","cited_by_count":23,"area":"mllm"},{"id":"2512.16676","title":"DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI","created":"2025-12-18","cited_by_count":23,"area":null},{"id":"2410.09335","title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","created":"2024-10-12","cited_by_count":22,"area":"lr"},{"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":"2602.05400","title":"OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration","created":"2026-02-05","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":"2411.11504","title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","created":"2024-11-18","cited_by_count":16,"area":null},{"id":"2411.04425","title":"DELIFT: Data Efficient Language model Instruction Fine Tuning","created":"2024-11-07","cited_by_count":14,"area":null},{"id":"2404.01067","title":"Exploring the Mystery of Influential Data for Mathematical Reasoning","created":"2024-04-01","cited_by_count":13,"area":"lr"},{"id":"2410.15225","title":"Chasing Random: Instruction Selection Strategies Fail to Generalize","created":"2024-10-19","cited_by_count":13,"area":null},{"id":"2406.14115","title":"Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models","created":"2024-06-20","cited_by_count":12,"area":"lr"},{"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":"2408.01323","title":"FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only","created":"2024-08-02","cited_by_count":11,"area":null},{"id":"2407.21669","title":"Synth-Empathy: Towards High-Quality Synthetic Empathy Data","created":"2024-07-31","cited_by_count":10,"area":null},{"id":"2410.23463","title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","created":"2024-10-30","cited_by_count":10,"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":"2412.06293","title":"Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness","created":"2024-12-09","cited_by_count":10,"area":"mllm"},{"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":"2504.01400","title":"ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning","created":"2025-04-02","cited_by_count":9,"area":"agents"},{"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":"2402.19273","title":"PlanGPT: Enhancing Urban Planning with Tailored Language Model and Efficient Retrieval","created":"2024-02-29","cited_by_count":8,"area":null},{"id":"2407.06027","title":"PAS: Data-Efficient Plug-and-Play Prompt Augmentation System","created":"2024-07-08","cited_by_count":7,"area":null},{"id":"2410.05090","title":"HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation","created":"2024-10-07","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":"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":"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":"2407.20756","title":"SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models","created":"2024-07-30","cited_by_count":6,"area":"mllm"},{"id":"2407.21055","title":"Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applications","created":"2024-07-24","cited_by_count":6,"area":"rag"},{"id":"2410.05639","title":"DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models","created":"2024-10-08","cited_by_count":6,"area":null},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2509.26497","title":"Revealing the Power of Post-Training for Small Language Models via Knowledge Distillation","created":"2025-09-30","cited_by_count":6,"area":"distill"},{"id":"2411.10163","title":"Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions","created":"2024-11-15","cited_by_count":5,"area":null},{"id":"2412.12865","title":"Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models","created":"2024-12-17","cited_by_count":5,"area":"alignment"},{"id":"2603.26164","title":"DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models","created":"2026-03-27","cited_by_count":5,"area":null},{"id":"2406.17305","title":"Retrieval Augmented Instruction Tuning for Open NER with Large Language Models","created":"2024-06-25","cited_by_count":4,"area":"rag"},{"id":"2504.14810","title":"DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning","created":"2025-04-21","cited_by_count":4,"area":null},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2403.06131","title":"PPFedIT: Towards Privacy-Preserving Federated Instruction Tuning with Few-shot Local Examples","created":"2024-03-10","cited_by_count":3,"area":"safety"},{"id":"2410.10901","title":"3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection","created":"2024-10-13","cited_by_count":3,"area":null},{"id":"2411.15484","title":"Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai","created":"2024-11-23","cited_by_count":3,"area":"synth"},{"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":"2505.18557","title":"TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation","created":"2025-05-24","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":"2508.19996","title":"ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2603.14712","title":"Towards Next-Generation LLM Training: From the Data-Centric Perspective","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2605.30288","title":"MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.00400","title":"Dynamic Proxy-Mixing: Transferring Replay Controllers from Small to Large Models for Continual Instruction Tuning","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2606.07001","title":"DataEvolver: Automatic Data Preparation for Large Language Models through Multi-Level Self-Evolving","created":"2026-06-05","cited_by_count":3,"area":"synth"},{"id":"2408.15915","title":"Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models","created":"2024-08-28","cited_by_count":2,"area":"moe"},{"id":"2409.00997","title":"DataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective Partitioning","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2409.18541","title":"Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation","created":"2024-09-27","cited_by_count":2,"area":"mllm"},{"id":"2505.14481","title":"PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models","created":"2025-05-20","cited_by_count":2,"area":"mllm"},{"id":"2409.17527","title":"Data Proportion Detection for Optimized Data Management for Large Language Models","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2410.11540","title":"Data Quality Control in Federated Instruction-tuning of Large Language Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2412.06575","title":"Data Quality Enhancement on the Basis of Diversity with Large Language Models for Text Classification: Uncovered, Difficult, and Noisy","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2503.01131","title":"Beyond QA Pairs: Assessing Parameter-Efficient Fine-Tuning for Fact Embedding in LLMs","created":"2025-03-03","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":"2505.05122","title":"Text2Cypher: Data Pruning using Hard Example Selection","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2505.12754","title":"ProDS: Preference-oriented Data Selection for Instruction Tuning","created":"2025-05-19","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":"2509.01221","title":"DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression","created":"2025-09-01","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":"2407.01937","title":"Efficient-Empathy: Towards Efficient and Effective Selection of Empathy Data","created":"2024-07-02","cited_by_count":0,"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":"2503.24028","title":"Pay More Attention to the Robustness of Prompt for Instruction Data Mining","created":"2025-03-31","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":"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":"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}],"next_cursor":"100"}