{"total":100,"rows":[{"id":"2407.11005","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","created":"2024-06-25","cited_by_count":117,"area":"rag"},{"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":"2406.00793","title":"Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective","created":"2024-06-02","cited_by_count":57,"area":null},{"id":"2503.19633","title":"1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training","created":"2025-03-25","cited_by_count":49,"area":"lr"},{"id":"2408.05534","title":"Can LLMs Replace Manual Annotation of Software Engineering Artifacts?","created":"2024-08-10","cited_by_count":42,"area":null},{"id":"2409.07486","title":"MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model","created":"2024-09-04","cited_by_count":28,"area":null},{"id":"2409.15723","title":"Federated Large Language Models: Current Progress and Future Directions","created":"2024-09-24","cited_by_count":27,"area":null},{"id":"2504.14772","title":"Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions","created":"2025-04-20","cited_by_count":26,"area":"distill"},{"id":"2403.13335","title":"Adaptive Ensembles of Fine-Tuned Transformers for LLM-Generated Text Detection","created":"2024-03-20","cited_by_count":22,"area":null},{"id":"2310.17876","title":"TarGEN: Targeted Data Generation with Large Language Models","created":"2023-10-27","cited_by_count":17,"area":null},{"id":"2504.20068","title":"JITServe: SLO-aware LLM Serving with Imprecise Request Information","created":"2025-04-24","cited_by_count":17,"area":"inference"},{"id":"2406.01457","title":"Differentially Private Tabular Data Synthesis using Large Language Models","created":"2024-06-03","cited_by_count":16,"area":"synth"},{"id":"2406.12480","title":"The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions","created":"2024-06-18","cited_by_count":16,"area":"synth"},{"id":"2410.01720","title":"Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective","created":"2024-10-02","cited_by_count":15,"area":"synth"},{"id":"2505.12781","title":"A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone","created":"2025-05-19","cited_by_count":15,"area":"distill"},{"id":"2406.04619","title":"CTSyn: A Foundation Model for Cross Tabular Data Generation","created":"2024-06-07","cited_by_count":14,"area":"diffusion"},{"id":"2403.19839","title":"The New Agronomists: Language Models are Experts in Crop Management","created":"2024-03-28","cited_by_count":13,"area":null},{"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":"2404.04293","title":"Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding","created":"2024-04-04","cited_by_count":12,"area":"lr"},{"id":"2502.17607","title":"Synthetic Text Generation for Training Large Language Models via Gradient Matching","created":"2025-02-24","cited_by_count":10,"area":null},{"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":"2411.03250","title":"DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models","created":"2024-11-05","cited_by_count":9,"area":"diffusion"},{"id":"2404.14445","title":"A Multi-Faceted Evaluation Framework for Assessing Synthetic Data Generated by Large Language Models","created":"2024-04-20","cited_by_count":8,"area":"synth"},{"id":"2410.17781","title":"Evaluating Explanations Through LLMs: Beyond Traditional User Studies","created":"2024-10-23","cited_by_count":8,"area":null},{"id":"2410.22182","title":"Synthetic Data Generation with Large Language Models for Personalized Community Question Answering","created":"2024-10-29","cited_by_count":8,"area":"synth"},{"id":"2502.18641","title":"WhatELSE: Shaping Narrative Spaces at Configurable Level of Abstraction for AI-bridged Interactive Storytelling","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2412.07030","title":"FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering","created":"2024-12-09","cited_by_count":7,"area":"synth"},{"id":"2505.14212","title":"Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2410.21526","title":"Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification","created":"2024-10-28","cited_by_count":6,"area":"lr"},{"id":"2410.18436","title":"Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching","created":"2024-10-24","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":"2501.15108","title":"Knowledge Hierarchy Guided Biological-Medical Dataset Distillation for Domain LLM Training","created":"2025-01-25","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":"2503.04736","title":"Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2407.08597","title":"Learning Program Behavioral Models from Synthesized Input-Output Pairs","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2408.04867","title":"An Evaluation of Standard Statistical Models and LLMs on Time Series Forecasting","created":"2024-08-09","cited_by_count":4,"area":null},{"id":"2409.18003","title":"Enhancing Tourism Recommender Systems for Sustainable City Trips Using Retrieval-Augmented Generation","created":"2024-09-26","cited_by_count":4,"area":"rag"},{"id":"2502.00808","title":"Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications","created":"2025-02-02","cited_by_count":4,"area":"synth"},{"id":"2404.12192","title":"Aligning Actions and Walking to LLM-Generated Textual Descriptions","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2405.06093","title":"Selective Fine-tuning on LLM-labeled Data May Reduce Reliance on Human Annotation: A Case Study Using Schedule-of-Event Table Detection","created":"2024-05-09","cited_by_count":3,"area":null},{"id":"2405.15289","title":"Learning Invariant Causal Mechanism from Vision-Language Models","created":"2024-05-24","cited_by_count":3,"area":"mllm"},{"id":"2503.20568","title":"Low-resource Information Extraction with the European Clinical Case Corpus","created":"2025-03-26","cited_by_count":3,"area":null},{"id":"2505.12236","title":"Bridging Generative and Discriminative Learning: Few-Shot Relation Extraction via Two-Stage Knowledge-Guided Pre-training","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2506.16594","title":"A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives","created":"2025-06-19","cited_by_count":3,"area":"synth"},{"id":"2509.16543","title":"ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions","created":"2025-09-20","cited_by_count":3,"area":"synth"},{"id":"2510.18250","title":"ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2512.14562","title":"Polypersona: Persona-Grounded LLM for Synthetic Survey Responses","created":"2025-12-16","cited_by_count":3,"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":"2504.15432","title":"Feeding LLM Annotations to BERT Classifiers at Your Own Risk","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2506.00277","title":"Hierarchical Level-Wise News Article Clustering via Multilingual Matryoshka Embeddings","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2507.18044","title":"Synthetic Data Generation for Phrase Break Prediction with Large Language Model","created":"2025-07-24","cited_by_count":2,"area":"synth"},{"id":"2508.04337","title":"Modelling and Classifying the Components of a Literature Review","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2510.04682","title":"TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2511.03023","title":"PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Framework","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2511.03928","title":"SynQuE: Estimating Synthetic Dataset Quality Without Annotations","created":"2025-11-06","cited_by_count":2,"area":"synth"},{"id":"2601.06225","title":"Classroom AI: Large Language Models as Grade-Specific Teachers","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2602.12143","title":"STAR : Bridging Statistical and Agentic Reasoning for Large Model Performance Prediction","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2604.23904","title":"Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities","created":"2026-04-26","cited_by_count":2,"area":"synth"},{"id":"2406.14425","title":"SynDARin: Synthesising Datasets for Automated Reasoning in Low-Resource Languages","created":"2024-06-20","cited_by_count":1,"area":"lr"},{"id":"2407.14371","title":"Open Artificial Knowledge","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2410.16882","title":"SaVe-TAG: LLM-based Interpolation for Long-Tailed Text-Attributed Graphs","created":"2024-10-22","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":"2501.01963","title":"Statistical learning does not always entail knowledge","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2504.03877","title":"Concept-based Rubrics Improve LLM Formative Assessment and Data Synthesis","created":"2025-04-04","cited_by_count":1,"area":"synth"},{"id":"2504.06010","title":"Latent Reconstruction from Generated Data for Multimodal Misinformation Detection","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2504.17203","title":"High-Fidelity And Complex Test Data Generation For Google SQL Code Generation Services","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2504.19565","title":"Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training","created":"2025-04-28","cited_by_count":1,"area":"agents"},{"id":"2505.03265","title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2506.13494","title":"Watermarking LLM-Generated Datasets in Downstream Tasks","created":"2025-06-16","cited_by_count":1,"area":"safety"},{"id":"2506.19262","title":"What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning","created":"2025-06-24","cited_by_count":1,"area":"synth"},{"id":"2508.07087","title":"SQL-Exchange: Transforming SQL Queries Across Domains","created":"2025-08-09","cited_by_count":1,"area":null},{"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":"2510.16095","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":"2604.17803","title":"Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2402.16910","title":"NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification","created":"2024-02-25","cited_by_count":0,"area":null},{"id":"2501.06577","title":"Survey Transfer Learning: Recycling Data with Silicon Responses","created":"2025-01-11","cited_by_count":0,"area":null},{"id":"2502.09947","title":"Analyzing Patient Daily Movement Behavior Dynamics Using Two-Stage Encoding Model","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2502.15155","title":"Extreme Speech Classification in the Era of LLMs: Exploring Open-Source and Proprietary Models","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2503.16433","title":"The Application of MATEC (Multi-AI Agent Team Care) Framework in Sepsis Care","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2505.02858","title":"Towards High-Fidelity Synthetic Multi-platform Social Media Datasets via Large Language Models","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2506.21138","title":"Multi-Sample Prompting and Actor-Critic Prompt Optimization for Diverse Synthetic Data Generation","created":"2025-06-26","cited_by_count":0,"area":"alignment"},{"id":"2508.10000","title":"AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2511.11591","title":"LLM-Generated Negative News Headlines Dataset: Creation and Benchmarking Against Real Journalism","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2511.21827","title":"Evaluating Strategies for Synthesizing Clinical Notes for Medical Multimodal AI","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2601.06033","title":"How Generative AI Empowers Attackers and Defenders Across the Trust & Safety Landscape","created":"2025-11-10","cited_by_count":0,"area":"safety"},{"id":"2601.21543","title":"inversedMixup: Data Augmentation via Inverting Mixed Embeddings","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.03119","title":"Function-Space Empirical Bayes Regularisation with Large Vision-Language Model Priors","created":"2026-02-03","cited_by_count":0,"area":"mllm"},{"id":"2602.16379","title":"Label-Consistent Data Generation for Aspect-Based Sentiment Analysis Using LLM Agents","created":"2026-02-18","cited_by_count":0,"area":"agents"},{"id":"2602.17465","title":"Entropy-Based Data Selection for Language Models","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.02420","title":"Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"id":"2603.11436","title":"ZTab: Domain-based Zero-shot Annotation for Table Columns","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.14163","title":"SeaAlert: Robust Severity Classification and LLM-Based Information Extraction for Noisy Maritime Distress Communications","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.21137","title":"Enhancing Science Classroom Discourse Analysis through Joint Multi-Task Learning for Reasoning-Component Classification","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2604.26986","title":"BatteryPass-12K: The First Dataset for the Novel Digital Battery Passport Conformance Task","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.27671","title":"Evolving and Detecting Multi-Turn Deception using Geometric Signatures","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.00143","title":"Hate Speech Detection in Turkish and Arabic: A Comprehensive Study","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.05761","title":"Synthetic Consumer Insight Generation with Large Language Models","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.13866","title":"Geometric Filtering of LLM-Generated Samples for Few-Shot Text Classification","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2610.15908","title":"LURE: a Phase-Labelled Synthetic Corpus of Online-Grooming Exchanges","created":"2026-10-11","cited_by_count":0,"area":"synth"},{"id":"2610.17077","title":"UZHCL_for_the_win at Touche: Encoder Fine-Tuning, Synthetic Augmentation, and an Underpowered Encoder-LLM Comparison","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}