{"total":130,"rows":[{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250,"area":null},{"id":"2305.18474","title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation","created":"2023-05-29","cited_by_count":90,"area":"diffusion"},{"id":"2401.11641","title":"Revolutionizing Finance with LLMs: An Overview of Applications and Insights","created":"2024-01-22","cited_by_count":90,"area":null},{"id":"2401.04334","title":"Large Language Models for Robotics: Opportunities, Challenges, and Perspectives","created":"2024-01-09","cited_by_count":89,"area":"mllm"},{"id":"2306.06283","title":"14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon","created":"2023-06-09","cited_by_count":86,"area":null},{"id":"2307.15780","title":"LLM-Rec: Personalized Recommendation via Prompting Large Language Models","created":"2023-07-24","cited_by_count":77,"area":null},{"id":"2309.11206","title":"Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering","created":"2023-09-20","cited_by_count":65,"area":null},{"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":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2409.00608","title":"TinyAgent: Function Calling at the Edge","created":"2024-09-01","cited_by_count":58,"area":"agents"},{"id":"2304.08448","title":"An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT","created":"2023-04-17","cited_by_count":57,"area":null},{"id":"2305.06566","title":"ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models","created":"2023-05-11","cited_by_count":54,"area":null},{"id":"2502.07049","title":"LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights","created":"2025-02-10","cited_by_count":47,"area":null},{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40,"area":null},{"id":"2401.10506","title":"FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis","created":"2024-01-19","cited_by_count":36,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2304.11567","title":"Differentiate ChatGPT-generated and Human-written Medical Texts","created":"2023-04-23","cited_by_count":26,"area":null},{"id":"2303.07610","title":"Exploring ChatGPT's Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences","created":"2023-03-14","cited_by_count":25,"area":null},{"id":"2405.13003","title":"A Survey on Recent Advances in Conversational Data Generation","created":"2024-05-12","cited_by_count":23,"area":null},{"id":"2310.06046","title":"LLM for SoC Security: A Paradigm Shift","created":"2023-10-09","cited_by_count":22,"area":null},{"id":"2310.18365","title":"Using GPT-4 to Augment Unbalanced Data for Automatic Scoring","created":"2023-10-25","cited_by_count":20,"area":null},{"id":"2310.09223","title":"Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation","created":"2023-10-13","cited_by_count":19,"area":null},{"id":"2312.05256","title":"Holistic Evaluation of GPT-4V for Biomedical Imaging","created":"2023-11-10","cited_by_count":19,"area":null},{"id":"2306.17459","title":"Harnessing LLMs in Curricular Design: Using GPT-4 to Support Authoring of Learning Objectives","created":"2023-06-30","cited_by_count":16,"area":null},{"id":"2402.11192","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","created":"2024-02-17","cited_by_count":15,"area":null},{"id":"2407.03263","title":"A Unified Framework for 3D Scene Understanding","created":"2024-07-03","cited_by_count":15,"area":null},{"id":"2408.08978","title":"See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses","created":"2024-08-16","cited_by_count":15,"area":null},{"id":"2307.02514","title":"Exploring Multimodal Approaches for Alzheimer's Disease Detection Using Patient Speech Transcript and Audio Data","created":"2023-07-05","cited_by_count":13,"area":null},{"id":"2405.13448","title":"Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning","created":"2024-05-22","cited_by_count":13,"area":null},{"id":"2307.13693","title":"Evaluating Large Language Models for Radiology Natural Language Processing","created":"2023-07-25","cited_by_count":12,"area":null},{"id":"2402.13482","title":"Retrieval-Augmented Data Augmentation for Low-Resource Domain Tasks","created":"2024-02-21","cited_by_count":12,"area":"rag"},{"id":"2410.05801","title":"Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation","created":"2024-10-08","cited_by_count":12,"area":"lr"},{"id":"2310.05318","title":"Resolving the Imbalance Issue in Hierarchical Disciplinary Topic Inference via LLM-based Data Augmentation","created":"2023-10-09","cited_by_count":11,"area":null},{"id":"2410.18808","title":"Delving into the Reversal Curse: How Far Can Large Language Models Generalize?","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2512.09619","title":"GLaD: Geometric Latent Distillation for Vision-Language-Action Models","created":"2025-12-10","cited_by_count":11,"area":"lr"},{"id":"2407.03672","title":"A Survey of Data Synthesis Approaches","created":"2024-07-04","cited_by_count":9,"area":"synth"},{"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":"2402.16515","title":"LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification","created":"2024-02-26","cited_by_count":8,"area":"distill"},{"id":"2403.09085","title":"Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance","created":"2024-03-14","cited_by_count":8,"area":"lr"},{"id":"2407.00322","title":"LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods","created":"2024-06-29","cited_by_count":8,"area":null},{"id":"2410.22239","title":"DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2502.16645","title":"CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale","created":"2025-02-23","cited_by_count":8,"area":"alignment"},{"id":"2401.00424","title":"SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection","created":"2023-12-31","cited_by_count":7,"area":null},{"id":"2405.15728","title":"Disease-informed Adaptation of Vision-Language Models","created":"2024-05-24","cited_by_count":7,"area":"mllm"},{"id":"2406.19614","title":"A Survey on Data Quality Dimensions and Tools for Machine Learning","created":"2024-06-28","cited_by_count":7,"area":null},{"id":"2407.07341","title":"A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches","created":"2024-07-10","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":"2512.04763","title":"MemLoRA: Distilling Expert Adapters for On-Device Memory Systems","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2306.07297","title":"Medical Data Augmentation via ChatGPT: A Case Study on Medication Identification and Medication Event Classification","created":"2023-06-10","cited_by_count":6,"area":null},{"id":"2309.05021","title":"Chat2Brain: A Method for Mapping Open-Ended Semantic Queries to Brain Activation Maps","created":"2023-09-10","cited_by_count":5,"area":null},{"id":"2310.20033","title":"Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","created":"2023-10-30","cited_by_count":5,"area":"alignment"},{"id":"2404.15974","title":"A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examples","created":"2024-04-24","cited_by_count":5,"area":"agents"},{"id":"2407.19405","title":"Logic Distillation: Learning from Code Function by Function for Decision-making Tasks","created":"2024-07-28","cited_by_count":5,"area":"lr"},{"id":"2502.08512","title":"Measuring Diversity in Synthetic Datasets","created":"2025-02-12","cited_by_count":5,"area":"synth"},{"id":"2506.03484","title":"Explainable AI: XAI-Guided Context-Aware Data Augmentation","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2311.04368","title":"Evaluating multiple large language models in pediatric ophthalmology","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2403.15214","title":"InstaSynth: Opportunities and Challenges in Generating Synthetic Instagram Data with ChatGPT for Sponsored Content Detection","created":"2024-03-22","cited_by_count":4,"area":null},{"id":"2411.13045","title":"Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning","created":"2024-11-20","cited_by_count":4,"area":"distill"},{"id":"2412.14809","title":"ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis","created":"2024-12-19","cited_by_count":4,"area":"synth"},{"id":"2602.12394","title":"Synthetic Interaction Data for Scalable Personalization in Large Language Models","created":"2026-02-12","cited_by_count":4,"area":null},{"id":"2403.15715","title":"EDDA: A Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection","created":"2024-03-23","cited_by_count":3,"area":null},{"id":"2406.08718","title":"Enhancing Psychotherapy Counseling: A Data Augmentation Pipeline Leveraging Large Language Models for Counseling Conversations","created":"2024-06-13","cited_by_count":3,"area":null},{"id":"2410.08442","title":"JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensembles","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2410.15365","title":"BERTtime Stories: Investigating the Role of Synthetic Story Data in Language Pre-training","created":"2024-10-20","cited_by_count":3,"area":null},{"id":"2411.14896","title":"Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2509.16543","title":"ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions","created":"2025-09-20","cited_by_count":3,"area":"synth"},{"id":"2403.08502","title":"Masked Generative Story Transformer with Character Guidance and Caption Augmentation","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2405.06695","title":"Utilizing Large Language Models to Generate Synthetic Data to Increase the Performance of BERT-Based Neural Networks","created":"2024-05-08","cited_by_count":2,"area":"synth"},{"id":"2406.16567","title":"Data Augmentation of Multi-turn Psychological Dialogue via Knowledge-driven Progressive Thought Prompting","created":"2024-06-24","cited_by_count":2,"area":"lr"},{"id":"2408.11431","title":"Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2412.09706","title":"Diffusion-Enhanced Test-time Adaptation with Text and Image Augmentation","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2412.14849","title":"DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis","created":"2024-12-19","cited_by_count":2,"area":"synth"},{"id":"2505.15255","title":"Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2507.14590","title":"Backtranslation and paraphrasing in the LLM era? Comparing data augmentation methods for emotion classification","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2510.18143","title":"Learning from Generalization Patterns: An Evaluation-Driven Approach to Enhanced Data Augmentation for Fine-Tuning Small Language Models","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2312.13557","title":"Empowering Few-Shot Recommender Systems with Large Language Models -- Enhanced Representations","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2401.13588","title":"Evaluation of General Large Language Models in Contextually Assessing Semantic Concepts Extracted from Adult Critical Care Electronic Health Record Notes","created":"2024-01-24","cited_by_count":1,"area":null},{"id":"2401.16349","title":"ConFit: Improving Resume-Job Matching using Data Augmentation and Contrastive Learning","created":"2024-01-29","cited_by_count":1,"area":null},{"id":"2402.05584","title":"AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2403.08352","title":"Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2404.16198","title":"Towards Efficient Patient Recruitment for Clinical Trials: Application of a Prompt-Based Learning Model","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2407.14765","title":"Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs","created":"2024-07-20","cited_by_count":1,"area":null},{"id":"2409.00061","title":"Enhancing Natural Language Inference Performance with Knowledge Graph for COVID-19 Automated Fact-Checking in Indonesian Language","created":"2024-08-22","cited_by_count":1,"area":null},{"id":"2410.09564","title":"Extended Japanese Commonsense Morality Dataset with Masked Token and Label Enhancement","created":"2024-10-12","cited_by_count":1,"area":null},{"id":"2411.06175","title":"Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs","created":"2024-11-09","cited_by_count":1,"area":null},{"id":"2412.09859","title":"Financial Sentiment Analysis: Leveraging Actual and Synthetic Data for Supervised Fine-tuning","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2503.06949","title":"LexPro-1.0 Technical Report","created":"2025-03-10","cited_by_count":1,"area":"lr"},{"id":"2504.14241","title":"A Knowledge-Informed Deep Learning Paradigm for Generalizable and Stability-Optimized Car-Following Models","created":"2025-04-19","cited_by_count":1,"area":null},{"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":"2508.21083","title":"CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.02668","title":"AgenticRAG: Tool-Augmented Foundation Models for Zero-Shot Explainable Recommender Systems","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2512.10178","title":"CIEGAD: Cluster-Conditioned Interpolative and Extrapolative Framework for Geometry-Aware and Domain-Aligned Data Augmentation","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2602.14536","title":"Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.10823","title":"ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning","created":"2026-03-11","cited_by_count":1,"area":"synth"},{"id":"2603.22765","title":"DALDALL: Data Augmentation for Lexical and Semantic Diverse in Legal Domain by leveraging LLM-Persona","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.27014","title":"Fidelity, Diversity, and Privacy: A Multi-Dimensional LLM Evaluation for Clinical Data Augmentation","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2607.17043","title":"Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning","created":"2026-07-19","cited_by_count":1,"area":"synth"},{"id":"2609.33763","title":"SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilities","created":"2026-09-27","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}