{"total":106,"rows":[{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413,"area":"mllm"},{"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":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244,"area":"synth"},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2405.19332","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","created":"2024-05-29","cited_by_count":63,"area":"alignment"},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"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":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"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":"2410.12952","title":"Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning","created":"2024-10-16","cited_by_count":42,"area":"agents"},{"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":"2505.00661","title":"On the generalization of language models from in-context learning and finetuning: a controlled study","created":"2025-05-01","cited_by_count":40,"area":"lr"},{"id":"2409.17115","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","created":"2024-09-25","cited_by_count":37,"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":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2410.18798","title":"Distill Visual Chart Reasoning Ability from LLMs to MLLMs","created":"2024-10-24","cited_by_count":31,"area":"lr"},{"id":"2410.02677","title":"CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming","created":"2024-10-03","cited_by_count":30,"area":null},{"id":"2510.09781","title":"Building a Foundational Guardrail for General Agentic Systems via Synthetic Data","created":"2025-10-10","cited_by_count":29,"area":"agents"},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26,"area":"lr"},{"id":"2412.14689","title":"How to Synthesize Text Data without Model Collapse?","created":"2024-12-19","cited_by_count":25,"area":"synth"},{"id":"2410.14251","title":"Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation","created":"2024-10-18","cited_by_count":24,"area":"agents"},{"id":"2412.11605","title":"SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models","created":"2024-12-16","cited_by_count":23,"area":"lr"},{"id":"2407.07053","title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model","created":"2024-07-09","cited_by_count":21,"area":"lr"},{"id":"2405.01886","title":"Aloe: A Family of Fine-tuned Open Healthcare LLMs","created":"2024-05-03","cited_by_count":20,"area":"safety"},{"id":"2406.05184","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","created":"2024-06-07","cited_by_count":19,"area":null},{"id":"2410.11076","title":"PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries","created":"2024-10-14","cited_by_count":19,"area":null},{"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":"2410.04638","title":"Provable Weak-to-Strong Generalization via Benign Overfitting","created":"2024-10-06","cited_by_count":16,"area":"distill"},{"id":"2410.12138","title":"Preference Optimization with Multi-Sample Comparisons","created":"2024-10-16","cited_by_count":16,"area":"diffusion"},{"id":"2411.07133","title":"Stronger Models are NOT Stronger Teachers for Instruction Tuning","created":"2024-11-11","cited_by_count":16,"area":null},{"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":"2410.05464","title":"Progressive distillation induces an implicit curriculum","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2409.12929","title":"LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning","created":"2024-09-19","cited_by_count":14,"area":"lr"},{"id":"2406.12397","title":"Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models","created":"2024-06-18","cited_by_count":13,"area":"synth"},{"id":"2410.14208","title":"Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning","created":"2024-10-18","cited_by_count":13,"area":null},{"id":"2411.19930","title":"On Domain-Adaptive Post-Training for Multimodal Large Language Models","created":"2024-11-29","cited_by_count":13,"area":"mllm"},{"id":"2410.03083","title":"Scaling Parameter-Constrained Language Models with Quality Data","created":"2024-10-04","cited_by_count":12,"area":null},{"id":"2502.14044","title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"id":"2510.10331","title":"LLM-Friendly Knowledge Representation for Customer Support","created":"2025-10-11","cited_by_count":12,"area":null},{"id":"2406.12442","title":"Abstraction-of-Thought Makes Language Models Better Reasoners","created":"2024-06-18","cited_by_count":11,"area":"lr"},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2410.18634","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2410.22316","title":"Understanding Synthetic Context Extension via Retrieval Heads","created":"2024-10-29","cited_by_count":10,"area":"rag"},{"id":"2407.03672","title":"A Survey of Data Synthesis Approaches","created":"2024-07-04","cited_by_count":9,"area":"synth"},{"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":"2404.18043","title":"Utilizing Large Language Models for Information Extraction from Real Estate Transactions","created":"2024-04-28","cited_by_count":8,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2408.13467","title":"LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs","created":"2024-08-24","cited_by_count":8,"area":null},{"id":"2410.03884","title":"KidLM: Advancing Language Models for Children -- Early Insights and Future Directions","created":"2024-10-04","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":"2406.12606","title":"Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment","created":"2024-06-18","cited_by_count":7,"area":"alignment"},{"id":"2410.16736","title":"Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration","created":"2024-10-22","cited_by_count":7,"area":"synth"},{"id":"2406.16694","title":"Task Oriented In-Domain Data Augmentation","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2407.16724","title":"Structure-aware Domain Knowledge Injection for Large Language Models","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2410.20297","title":"Fine-Tuning and Evaluating Open-Source Large Language Models for the Army Domain","created":"2024-10-27","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":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"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":"2412.20641","title":"SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy","created":"2024-12-30","cited_by_count":5,"area":"synth"},{"id":"2505.03906","title":"MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing","created":"2025-05-06","cited_by_count":5,"area":"agents"},{"id":"2405.16579","title":"Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity","created":"2024-05-26","cited_by_count":4,"area":null},{"id":"2502.11284","title":"Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning","created":"2025-02-16","cited_by_count":4,"area":"alignment"},{"id":"2503.12167","title":"PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2504.05755","title":"Unraveling Human-AI Teaming: A Review and Outlook","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2509.23041","title":"Virus Infection Attack on LLMs: Your Poisoning Can Spread \"VIA\" Synthetic Data","created":"2025-09-27","cited_by_count":4,"area":"synth"},{"id":"2510.18982","title":"Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality","created":"2025-10-21","cited_by_count":4,"area":"lr"},{"id":"2406.00505","title":"Improving Text Generation on Images with Synthetic Captions","created":"2024-06-01","cited_by_count":3,"area":"diffusion"},{"id":"2410.17566","title":"Differentially Private Learning Needs Better Model Initialization and Self-Distillation","created":"2024-10-23","cited_by_count":3,"area":"distill"},{"id":"2503.03417","title":"When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2503.16031","title":"Deceptive Humor: A Synthetic Multilingual Benchmark Dataset for Bridging Fabricated Claims with Humorous Content","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2506.14927","title":"MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance","created":"2025-06-17","cited_by_count":3,"area":"lr"},{"id":"2408.04127","title":"Incorporating Spatial Awareness in Data-Driven Gesture Generation for Virtual Agents","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2410.20791","title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2502.15069","title":"Rare Disease Differential Diagnosis with Large Language Models at Scale: From Abdominal Actinomycosis to Wilson's Disease","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2503.08042","title":"LSC-Eval: A General Framework to Evaluate Methods for Assessing Dimensions of Lexical Semantic Change Using LLM-Generated Synthetic Data","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2508.04337","title":"Modelling and Classifying the Components of a Literature Review","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2508.21179","title":"Synthetic CVs To Build and Test Fairness-Aware Hiring Tools","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2511.10338","title":"BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages","created":"2025-11-13","cited_by_count":2,"area":"synth"},{"id":"2406.11354","title":"Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2407.00924","title":"EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correction","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2407.14371","title":"Open Artificial Knowledge","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2409.12597","title":"LARE: Latent Augmentation using Regional Embedding with Vision-Language Model","created":"2024-09-19","cited_by_count":1,"area":"mllm"},{"id":"2410.00558","title":"AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation","created":"2024-10-01","cited_by_count":1,"area":"distill"},{"id":"2505.20888","title":"EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models","created":"2025-05-27","cited_by_count":1,"area":"distill"},{"id":"2509.13047","title":"Multi-Model Synthetic Training for Mission-Critical Small Language Models","created":"2025-09-16","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":"2512.19512","title":"Anatomy-R1: Enhancing Anatomy Reasoning in Multimodal Large Language Models via Anatomical Similarity Curriculum and Group Diversity Augmentation","created":"2025-12-22","cited_by_count":1,"area":"lr"},{"id":"2601.17829","title":"Linguistic and Argument Diversity in Synthetic Data for Function-Calling Agents","created":"2026-01-25","cited_by_count":1,"area":"agents"},{"id":"2603.18361","title":"Synthetic Data Generation for Training Diversified Commonsense Reasoning Models","created":"2026-03-18","cited_by_count":1,"area":"lr"},{"id":"2604.17803","title":"Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2607.08646","title":"UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2406.10764","title":"GNOME: Generating Negotiations through Open-Domain Mapping of Exchanges","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2410.04347","title":"Latent Feature Mining for Predictive Model Enhancement with Large Language Models","created":"2024-10-06","cited_by_count":0,"area":null},{"id":"2505.10640","title":"The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2505.22633","title":"Spatial Knowledge Graph-Guided Multimodal Synthesis","created":"2025-05-28","cited_by_count":0,"area":"mllm"},{"id":"2506.17847","title":"A Comparative Study of Open-Source Libraries for Synthetic Tabular Data Generation: SDV vs. SynthCity","created":"2025-06-21","cited_by_count":0,"area":null},{"id":"2511.19899","title":"VeriSciQA: An Auto-Verified Dataset for Scientific Visual Question Answering","created":"2025-11-25","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}