{"total":244,"rows":[{"id":"2407.21772","title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","created":"2024-07-31","cited_by_count":243,"area":null},{"id":"2504.07164","title":"R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents","created":"2025-04-09","cited_by_count":158,"area":"lr"},{"id":"2411.03350","title":"A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness","created":"2024-11-04","cited_by_count":127,"area":null},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119,"area":"lr"},{"id":"2503.14023","title":"Synthetic Data Generation Using Large Language Models: Advances in Text and Code","created":"2025-03-18","cited_by_count":61,"area":"synth"},{"id":"2410.15226","title":"On the Diversity of Synthetic Data and its Impact on Training Large Language Models","created":"2024-10-19","cited_by_count":59,"area":"synth"},{"id":"2508.03682","title":"Self-Questioning Language Models","created":"2025-08-05","cited_by_count":50,"area":null},{"id":"2409.11404","title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","created":"2024-09-17","cited_by_count":46,"area":null},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"area":"synth"},{"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":"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":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2508.04482","title":"OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use","created":"2025-08-06","cited_by_count":35,"area":"agents"},{"id":"2410.15413","title":"A Comprehensive Evaluation of Cognitive Biases in LLMs","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2503.04176","title":"TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records","created":"2025-03-06","cited_by_count":34,"area":null},{"id":"2507.23751","title":"CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks","created":"2025-07-31","cited_by_count":32,"area":"lr"},{"id":"2502.12378","title":"Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges","created":"2025-02-17","cited_by_count":31,"area":null},{"id":"2409.11968","title":"Efficacy of Synthetic Data as a Benchmark","created":"2024-09-18","cited_by_count":30,"area":"synth"},{"id":"2502.09977","title":"LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing","created":"2025-02-14","cited_by_count":29,"area":"rag"},{"id":"2412.11142","title":"AD-LLM: Benchmarking Large Language Models for Anomaly Detection","created":"2024-12-15","cited_by_count":26,"area":null},{"id":"2510.01631","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","created":"2025-10-02","cited_by_count":26,"area":"synth"},{"id":"2502.14860","title":"ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning","created":"2025-02-20","cited_by_count":25,"area":"lr"},{"id":"2503.13502","title":"Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2412.03920","title":"A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios","created":"2024-12-05","cited_by_count":23,"area":"agents"},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"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":"2603.09206","title":"MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data","created":"2026-03-10","cited_by_count":21,"area":"lr"},{"id":"2412.10136","title":"Can LLMs Convert Graphs to Text-Attributed Graphs?","created":"2024-12-13","cited_by_count":19,"area":null},{"id":"2409.11703","title":"Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation","created":"2024-09-18","cited_by_count":17,"area":"synth"},{"id":"2601.05111","title":"Agent-as-a-Judge","created":"2026-01-08","cited_by_count":17,"area":"agents"},{"id":"2409.06446","title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data","created":"2024-09-10","cited_by_count":16,"area":null},{"id":"2502.05605","title":"Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization","created":"2025-02-08","cited_by_count":16,"area":"lr"},{"id":"2407.08583","title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","created":"2024-07-11","cited_by_count":15,"area":"mllm"},{"id":"2409.19759","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","created":"2024-09-29","cited_by_count":15,"area":"synth"},{"id":"2503.11411","title":"Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models","created":"2025-03-14","cited_by_count":15,"area":"synth"},{"id":"2510.10925","title":"Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation","created":"2025-10-13","cited_by_count":15,"area":"synth"},{"id":"2412.13169","title":"Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study","created":"2024-12-17","cited_by_count":14,"area":null},{"id":"2506.16383","title":"Large Language Models in Argument Mining: A Survey","created":"2025-06-19","cited_by_count":14,"area":"rag"},{"id":"2502.04362","title":"LLMs can be easily Confused by Instructional Distractions","created":"2025-02-05","cited_by_count":13,"area":null},{"id":"2504.00573","title":"Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models","created":"2025-04-01","cited_by_count":13,"area":"rag"},{"id":"2410.03083","title":"Scaling Parameter-Constrained Language Models with Quality Data","created":"2024-10-04","cited_by_count":12,"area":null},{"id":"2411.14962","title":"LLM for Barcodes: Generating Diverse Synthetic Data for Identity Documents","created":"2024-11-22","cited_by_count":12,"area":"synth"},{"id":"2412.04494","title":"MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification","created":"2024-11-28","cited_by_count":12,"area":"agents"},{"id":"2502.18635","title":"Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems","created":"2025-02-25","cited_by_count":12,"area":"rag"},{"id":"2411.13768","title":"Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture","created":"2024-11-21","cited_by_count":11,"area":"agents"},{"id":"2502.08924","title":"Escaping Collapse: The Strength of Weak Data for Large Language Model Training","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2503.01900","title":"LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detection","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2509.08494","title":"HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2407.11784","title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2411.11053","title":"SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation","created":"2024-11-17","cited_by_count":10,"area":"lr"},{"id":"2502.08661","title":"Few-shot LLM Synthetic Data with Distribution Matching","created":"2025-02-09","cited_by_count":10,"area":"synth"},{"id":"2503.16585","title":"Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions","created":"2025-03-20","cited_by_count":10,"area":"mllm"},{"id":"2506.03448","title":"RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions","created":"2025-06-03","cited_by_count":10,"area":null},{"id":"2607.22529","title":"Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills","created":"2026-07-24","cited_by_count":10,"area":"synth"},{"id":"2411.03250","title":"DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models","created":"2024-11-05","cited_by_count":9,"area":"diffusion"},{"id":"2504.12322","title":"A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis","created":"2025-04-11","cited_by_count":9,"area":"synth"},{"id":"2505.22830","title":"What Has Been Lost with Synthetic Evaluation?","created":"2025-05-28","cited_by_count":9,"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":"2601.08198","title":"Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs","created":"2026-01-13","cited_by_count":9,"area":"synth"},{"id":"2601.17058","title":"Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs","created":"2026-01-22","cited_by_count":9,"area":null},{"id":"2411.19710","title":"Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems","created":"2024-11-29","cited_by_count":8,"area":"rag"},{"id":"2502.15419","title":"Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking","created":"2025-02-21","cited_by_count":8,"area":null},{"id":"2505.20416","title":"GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation","created":"2025-05-26","cited_by_count":8,"area":"synth"},{"id":"2510.10182","title":"A Survey of Inductive Reasoning for Large Language Models","created":"2025-10-11","cited_by_count":8,"area":"lr"},{"id":"2410.02056","title":"Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data","created":"2024-10-02","cited_by_count":7,"area":"synth"},{"id":"2410.09168","title":"Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications","created":"2024-10-11","cited_by_count":7,"area":"synth"},{"id":"2502.01683","title":"LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2504.15548","title":"LLM-based Semantic Augmentation for Harmful Content Detection","created":"2025-04-22","cited_by_count":7,"area":"safety"},{"id":"2507.07229","title":"SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2510.19361","title":"AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation","created":"2025-10-22","cited_by_count":7,"area":"lr"},{"id":"2502.05467","title":"Position: LLMs Can be Good Tutors in English Education","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2503.09956","title":"DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2505.00022","title":"Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation","created":"2025-04-24","cited_by_count":6,"area":"synth"},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2509.10886","title":"CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis","created":"2025-09-13","cited_by_count":6,"area":"rag"},{"id":"2409.07489","title":"RAGent: Retrieval-based Access Control Policy Generation","created":"2024-09-08","cited_by_count":5,"area":null},{"id":"2410.05021","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2411.10156","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","created":"2024-11-15","cited_by_count":5,"area":"alignment"},{"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":"2502.08512","title":"Measuring Diversity in Synthetic Datasets","created":"2025-02-12","cited_by_count":5,"area":"synth"},{"id":"2503.17739","title":"Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection","created":"2025-03-22","cited_by_count":5,"area":"synth"},{"id":"2506.03857","title":"Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation","created":"2025-06-04","cited_by_count":5,"area":"distill"},{"id":"2506.20274","title":"Enterprise Large Language Model Evaluation Benchmark","created":"2025-06-25","cited_by_count":5,"area":null},{"id":"2507.06968","title":"Scaling Towards the Information Boundary of Instruction Sets: The Infinity Instruct Subject Technical Report","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2508.08386","title":"CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation","created":"2025-08-11","cited_by_count":5,"area":"lr"},{"id":"2509.02040","title":"Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation","created":"2025-09-02","cited_by_count":5,"area":"synth"},{"id":"2510.19806","title":"The Art of Asking: Multilingual Prompt Optimization for Synthetic Data","created":"2025-10-22","cited_by_count":5,"area":"synth"},{"id":"2412.09807","title":"LLM Distillation for Efficient Few-Shot Multiple Choice Question Answering","created":"2024-12-13","cited_by_count":4,"area":null},{"id":"2502.00322","title":"MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections","created":"2025-02-01","cited_by_count":4,"area":null},{"id":"2502.11533","title":"Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2503.12999","title":"Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs","created":"2025-03-17","cited_by_count":4,"area":"mllm"},{"id":"2503.22006","title":"Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without Them","created":"2025-03-27","cited_by_count":4,"area":"synth"},{"id":"2504.00513","title":"Leveraging LLMs for User Stories in AI Systems: UStAI Dataset","created":"2025-04-01","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":"2505.23838","title":"Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2506.08646","title":"TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning","created":"2025-06-10","cited_by_count":4,"area":"synth"},{"id":"2507.02804","title":"Multimodal Mathematical Reasoning with Diverse Solving Perspective","created":"2025-07-03","cited_by_count":4,"area":"lr"},{"id":"2508.01556","title":"Empowering Tabular Data Preparation with Language Models: Why and How?","created":"2025-08-03","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":"2601.09692","title":"Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection","created":"2026-01-14","cited_by_count":4,"area":null}],"next_cursor":"100"}