{"total":99,"rows":[{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417,"area":"synth"},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"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":"2403.02333","title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","created":"2024-03-04","cited_by_count":58,"area":"lr"},{"id":"2407.00121","title":"Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks","created":"2024-06-27","cited_by_count":52,"area":"agents"},{"id":"2505.20347","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","created":"2025-05-25","cited_by_count":51,"area":"lr"},{"id":"2502.08468","title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","created":"2025-02-12","cited_by_count":49,"area":"synth"},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"area":"synth"},{"id":"2506.18896","title":"ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs","created":"2025-06-23","cited_by_count":46,"area":"lr"},{"id":"2405.14365","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","created":"2024-05-23","cited_by_count":45,"area":"lr"},{"id":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"area":"synth"},{"id":"2410.06961","title":"Self-Boosting Large Language Models with Synthetic Preference Data","created":"2024-10-09","cited_by_count":40,"area":"alignment"},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2504.12285","title":"BitNet b1.58 2B4T Technical Report","created":"2025-04-16","cited_by_count":38,"area":null},{"id":"2605.10999","title":"SkillGen: Verified Inference-Time Agent Skill Synthesis","created":"2026-05-09","cited_by_count":36,"area":"agents"},{"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":"2410.12971","title":"Self-Pluralising Culture Alignment for Large Language Models","created":"2024-10-16","cited_by_count":31,"area":"alignment"},{"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":"2501.15427","title":"OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas","created":"2025-01-26","cited_by_count":25,"area":null},{"id":"2410.18693","title":"Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch","created":"2024-10-24","cited_by_count":24,"area":"lr"},{"id":"2406.12034","title":"Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts","created":"2024-06-17","cited_by_count":23,"area":"moe"},{"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":"2412.02674","title":"Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models","created":"2024-12-03","cited_by_count":18,"area":"synth"},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2411.07133","title":"Stronger Models are NOT Stronger Teachers for Instruction Tuning","created":"2024-11-11","cited_by_count":16,"area":null},{"id":"2407.03974","title":"LLM Roleplay: Simulating Human-Chatbot Interaction","created":"2024-07-04","cited_by_count":15,"area":null},{"id":"2502.19312","title":"FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users","created":"2025-02-26","cited_by_count":15,"area":"alignment"},{"id":"2405.17258","title":"$\\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2410.05258","title":"Differential Transformer","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2410.03717","title":"Revisiting the Superficial Alignment Hypothesis","created":"2024-09-27","cited_by_count":12,"area":"alignment"},{"id":"2410.05725","title":"KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server","created":"2024-10-08","cited_by_count":11,"area":"distill"},{"id":"2410.18634","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2407.16008","title":"Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation","created":"2024-07-22","cited_by_count":9,"area":"alignment"},{"id":"2502.16684","title":"WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2502.01697","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","created":"2025-02-03","cited_by_count":8,"area":"synth"},{"id":"2504.15573","title":"Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction","created":"2025-04-22","cited_by_count":8,"area":"synth"},{"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":"2508.04632","title":"IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards","created":"2025-08-06","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":"2512.05145","title":"Self-Improving VLM Judges Without Human Annotations","created":"2025-12-02","cited_by_count":7,"area":"mllm"},{"id":"2607.14186","title":"NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs","created":"2026-07-15","cited_by_count":7,"area":"agents"},{"id":"2406.16694","title":"Task Oriented In-Domain Data Augmentation","created":"2024-06-24","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":"2505.17134","title":"LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2506.03558","title":"ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch","created":"2025-06-04","cited_by_count":5,"area":"synth"},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2408.10392","title":"Value Alignment from Unstructured Text","created":"2024-08-19","cited_by_count":4,"area":"alignment"},{"id":"2412.12310","title":"Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion","created":"2024-12-16","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":"2505.17217","title":"Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs","created":"2025-05-22","cited_by_count":4,"area":"lr"},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"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":"2510.17715","title":"QueST: Incentivizing LLMs to Generate Difficult Problems","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2410.16534","title":"SoftSRV: Learn to Generate Targeted Synthetic Data","created":"2024-10-21","cited_by_count":3,"area":"synth"},{"id":"2503.14167","title":"Synthetic Clarification and Correction Dialogues about Data-Centric Tasks -- A Teacher-Student Approach","created":"2025-03-18","cited_by_count":3,"area":"distill"},{"id":"2506.23520","title":"ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data","created":"2025-06-30","cited_by_count":3,"area":"synth"},{"id":"2412.08864","title":"GRIP: A Graph-Based Reasoning Instruction Producer","created":"2024-12-12","cited_by_count":2,"area":"lr"},{"id":"2412.15652","title":"Error-driven Data-efficient Large Multimodal Model Tuning","created":"2024-12-20","cited_by_count":2,"area":"mllm"},{"id":"2502.04511","title":"Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis","created":"2025-02-06","cited_by_count":2,"area":"synth"},{"id":"2503.03656","title":"Robust Learning of Diverse Code Edits","created":"2025-03-05","cited_by_count":2,"area":null},{"id":"2503.24062","title":"Artificial Conversations, Real Results: Fostering Language Detection with Synthetic Data","created":"2025-03-31","cited_by_count":2,"area":"synth"},{"id":"2508.04428","title":"Building Scaffolding Dialogue Data with LLM-Simulated Novices","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2509.25203","title":"Generating High-Quality Datasets for Code Editing via Open-Source Language Models","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2407.06323","title":"When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails","created":"2024-07-08","cited_by_count":1,"area":"safety"},{"id":"2412.19361","title":"Dynamic Skill Adaptation for Large Language Models","created":"2024-12-26","cited_by_count":1,"area":null},{"id":"2501.12521","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","created":"2025-01-21","cited_by_count":1,"area":null},{"id":"2502.03843","title":"Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis","created":"2025-02-06","cited_by_count":1,"area":"alignment"},{"id":"2504.20426","title":"RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library","created":"2025-04-29","cited_by_count":1,"area":"lr"},{"id":"2505.12250","title":"Not All Documents Are What You Need for Extracting Instruction Tuning Data","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2505.16972","title":"From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2507.23440","title":"Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2510.06670","title":"PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch","created":"2025-10-08","cited_by_count":1,"area":"alignment"},{"id":"2510.06965","title":"EDUMATH: Generating Standards-aligned Educational Math Word Problems","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.16095","title":"Reliability of Large Language Model Generated Clinical Reasoning in Assisted Reproductive Technology: Blinded Comparative Evaluation Study","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2407.01046","title":"FRoG: Evaluating Fuzzy Reasoning of Generalized Quantifiers in Large Language Models","created":"2024-07-01","cited_by_count":0,"area":"lr"},{"id":"2501.07674","title":"CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory","created":"2025-01-13","cited_by_count":0,"area":"synth"},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2509.01053","title":"A Dynamic Fusion Model for Consistent Crisis Response","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2509.05605","title":"Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation","created":"2025-09-06","cited_by_count":0,"area":"alignment"},{"id":"2509.14281","title":"SCoGen: Scenario-Centric Graph-Based Synthesis of Real-World Code Problems","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2512.08965","title":"Financial Instruction Following Evaluation (FIFE)","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.07430","title":"KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.22146","title":"FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale","created":"2026-01-29","cited_by_count":0,"area":"synth"},{"id":"2602.03300","title":"R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?","created":"2026-02-03","cited_by_count":0,"area":"mllm"},{"id":"2603.18073","title":"Continually self-improving AI","created":"2026-03-18","cited_by_count":0,"area":"synth"},{"id":"2604.07147","title":"Dynamic Context Evolution for Scalable Synthetic Data Generation","created":"2026-04-08","cited_by_count":0,"area":"synth"},{"id":"2605.30039","title":"Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning","created":"2026-05-28","cited_by_count":0,"area":"synth"},{"id":"2607.20443","title":"GLAN-QnA-KR: A Seedless Taxonomy-Driven Korean Instruction Corpus","created":"2026-05-12","cited_by_count":0,"area":"moe"},{"id":"2607.27366","title":"BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences","created":"2026-07-29","cited_by_count":0,"area":"alignment"},{"id":"2608.20394","title":"A Factorial Ablation of a Speech-to-SFT Pipeline: Differential Effects on Data Quality and Downstream Transfer","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.23870","title":"Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.19155","title":"Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2610.00814","title":"Training-Aware Target Coverage for Synthetic Data Selection","created":"2026-09-30","cited_by_count":0,"area":"synth"},{"id":"2610.01039","title":"Bootstrapping Video Interaction Generation with Synthetic State Transitions","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}