{"total":93,"rows":[{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137,"area":"synth"},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735,"area":"synth"},{"id":"2303.04360","title":"Does Synthetic Data Generation of LLMs Help Clinical Text Mining?","created":"2023-03-08","cited_by_count":154,"area":"synth"},{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130,"area":"synth"},{"id":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128,"area":"synth"},{"id":"2310.07849","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","created":"2023-10-11","cited_by_count":100,"area":"synth"},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"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":"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":"2109.06270","title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","created":"2021-09-13","cited_by_count":33,"area":"synth"},{"id":"2403.04190","title":"Generative AI for Synthetic Data Generation: Methods, Challenges and the Future","created":"2024-03-07","cited_by_count":33,"area":"synth"},{"id":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28,"area":"synth"},{"id":"2409.08239","title":"Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources","created":"2024-09-12","cited_by_count":28,"area":"synth"},{"id":"2210.17541","title":"Zero-Shot Text Classification with Self-Training","created":"2022-10-31","cited_by_count":26,"area":"synth"},{"id":"2104.09791","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval","created":"2021-04-20","cited_by_count":25,"area":"synth"},{"id":"2110.01256","title":"Revisiting Self-Training for Few-Shot Learning of Language Model","created":"2021-10-04","cited_by_count":23,"area":"synth"},{"id":"2412.19363","title":"Large Language Models for Market Research: A Data-augmentation Approach","created":"2024-12-26","cited_by_count":20,"area":"synth"},{"id":"2108.12589","title":"Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems","created":"2021-08-28","cited_by_count":18,"area":"synth"},{"id":"2109.04319","title":"Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data","created":"2021-09-09","cited_by_count":17,"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":"2407.12835","title":"Regurgitative Training: The Value of Real Data in Training Large Language Models","created":"2024-07-03","cited_by_count":15,"area":"synth"},{"id":"2502.15654","title":"Machine-generated text detection prevents language model collapse","created":"2025-02-21","cited_by_count":14,"area":"synth"},{"id":"2109.08259","title":"Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU","created":"2021-09-17","cited_by_count":13,"area":"synth"},{"id":"2304.11872","title":"Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM","created":"2023-04-24","cited_by_count":12,"area":"synth"},{"id":"2410.15234","title":"Bias Amplification: Large Language Models as Increasingly Biased Media","created":"2024-10-19","cited_by_count":12,"area":"synth"},{"id":"2502.03824","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","created":"2025-02-06","cited_by_count":11,"area":"synth"},{"id":"2502.08661","title":"Few-shot LLM Synthetic Data with Distribution Matching","created":"2025-02-09","cited_by_count":10,"area":"synth"},{"id":"2507.16663","title":"Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs","created":"2025-07-22","cited_by_count":10,"area":"synth"},{"id":"2509.04575","title":"Bootstrapping Task Spaces for Self-Improvement","created":"2025-09-04","cited_by_count":10,"area":"synth"},{"id":"2110.06274","title":"LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners","created":"2021-10-12","cited_by_count":9,"area":"synth"},{"id":"2405.09335","title":"Prompting-based Synthetic Data Generation for Few-Shot Question Answering","created":"2024-05-15","cited_by_count":9,"area":"synth"},{"id":"2412.17171","title":"Enhancing Item Tokenization for Generative Recommendation through Self-Improvement","created":"2024-12-22","cited_by_count":9,"area":"synth"},{"id":"2410.10864","title":"Fill In The Gaps: Model Calibration and Generalization with Synthetic Data","created":"2024-10-07","cited_by_count":8,"area":"synth"},{"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":"2210.16613","title":"Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers","created":"2022-10-29","cited_by_count":7,"area":"synth"},{"id":"2404.02422","title":"Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data","created":"2024-04-03","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":"2101.04758","title":"Self-Training Pre-Trained Language Models for Zero- and Few-Shot Multi-Dialectal Arabic Sequence Labeling","created":"2021-01-12","cited_by_count":6,"area":"synth"},{"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":"2509.15248","title":"Synthetic bootstrapped pretraining","created":"2025-09-17","cited_by_count":6,"area":"synth"},{"id":"2601.21343","title":"Self-Improving Pretraining: using post-trained models to pretrain better models","created":"2026-01-29","cited_by_count":6,"area":"synth"},{"id":"2103.07449","title":"Cooperative Self-training of Machine Reading Comprehension","created":"2021-03-12","cited_by_count":5,"area":"synth"},{"id":"2310.10118","title":"Learning to Rank Context for Named Entity Recognition Using a Synthetic Dataset","created":"2023-10-16","cited_by_count":5,"area":"synth"},{"id":"2404.01720","title":"Self-Improvement Programming for Temporal Knowledge Graph Question Answering","created":"2024-04-02","cited_by_count":5,"area":"synth"},{"id":"2405.03845","title":"Self-Improving Customer Review Response Generation Based on LLMs","created":"2024-05-06","cited_by_count":5,"area":"synth"},{"id":"2409.01552","title":"Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs","created":"2024-09-03","cited_by_count":5,"area":"synth"},{"id":"2403.00964","title":"MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination Detection","created":"2024-03-01","cited_by_count":4,"area":"synth"},{"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":"2503.02878","title":"Language Models can Self-Improve at State-Value Estimation for Better Search","created":"2025-03-04","cited_by_count":4,"area":"synth"},{"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":"2306.06347","title":"DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies","created":"2023-06-10","cited_by_count":3,"area":"synth"},{"id":"2310.13022","title":"Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding","created":"2023-10-19","cited_by_count":3,"area":"synth"},{"id":"2508.20525","title":"Enhancing Health Fact-Checking with LLM-Generated Synthetic Data","created":"2025-08-28","cited_by_count":3,"area":"synth"},{"id":"2309.08777","title":"Self-training Strategies for Sentiment Analysis: An Empirical Study","created":"2023-09-15","cited_by_count":2,"area":"synth"},{"id":"2401.00575","title":"Neural Networks Against (and For) Self-Training: Classification with Small Labeled and Large Unlabeled Sets","created":"2023-12-31","cited_by_count":2,"area":"synth"},{"id":"2404.02534","title":"ANGOFA: Leveraging OFA Embedding Initialization and Synthetic Data for Angolan Language Model","created":"2024-04-03","cited_by_count":2,"area":"synth"},{"id":"2511.07044","title":"Evaluating Large Language Models for Anxiety, Depression, and Stress Detection: Insights into Prompting Strategies and Synthetic Data","created":"2025-11-10","cited_by_count":2,"area":"synth"},{"id":"2112.08787","title":"AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models","created":"2021-12-16","cited_by_count":1,"area":"synth"},{"id":"2208.13376","title":"Reweighting Strategy based on Synthetic Data Identification for Sentence Similarity","created":"2022-08-29","cited_by_count":1,"area":"synth"},{"id":"2305.00076","title":"HausaNLP at SemEval-2023 Task 10: Transfer Learning, Synthetic Data and Side-Information for Multi-Level Sexism Classification","created":"2023-04-28","cited_by_count":1,"area":"synth"},{"id":"2405.20602","title":"Masked Language Modeling Becomes Conditional Density Estimation for Tabular Data Synthesis","created":"2024-05-31","cited_by_count":1,"area":"synth"},{"id":"2410.06845","title":"MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders","created":"2024-10-09","cited_by_count":1,"area":"synth"},{"id":"2410.10865","title":"Generating Synthetic Datasets for Few-shot Prompt Tuning","created":"2024-10-08","cited_by_count":1,"area":"synth"},{"id":"2411.00533","title":"ReverseNER: A Self-Generated Example-Driven Framework for Zero-Shot Named Entity Recognition with Large Language Models","created":"2024-11-01","cited_by_count":1,"area":"synth"},{"id":"2412.00657","title":"Improving Vietnamese Legal Document Retrieval using Synthetic Data","created":"2024-12-01","cited_by_count":1,"area":"synth"},{"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":"2512.12537","title":"NagaNLP: Bootstrapping NLP for Low-Resource Nagamese Creole with Human-in-the-Loop Synthetic Data","created":"2025-12-14","cited_by_count":1,"area":"synth"},{"id":"2305.18915","title":"Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures","created":"2023-05-30","cited_by_count":0,"area":"synth"},{"id":"2306.10414","title":"KEST: Kernel Distance Based Efficient Self-Training for Improving Controllable Text Generation","created":"2023-06-17","cited_by_count":0,"area":"synth"},{"id":"2310.19420","title":"Mean BERTs make erratic language teachers: the effectiveness of latent bootstrapping in low-resource settings","created":"2023-10-30","cited_by_count":0,"area":"synth"},{"id":"2312.04982","title":"Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification","created":"2023-12-08","cited_by_count":0,"area":"synth"},{"id":"2403.01163","title":"BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses","created":"2024-03-02","cited_by_count":0,"area":"synth"},{"id":"2406.09206","title":"Self-Training for Sample-Efficient Active Learning for Text Classification with Pre-Trained Language Models","created":"2024-06-13","cited_by_count":0,"area":"synth"},{"id":"2407.11854","title":"Zero-shot Cross-Lingual Transfer for Synthetic Data Generation in Grammatical Error Detection","created":"2024-07-16","cited_by_count":0,"area":"synth"},{"id":"2502.10263","title":"Large Language Models and Synthetic Data for Monitoring Dataset Mentions in Research Papers","created":"2025-02-14","cited_by_count":0,"area":"synth"},{"id":"2504.14808","title":"On Self-improving Token Embeddings","created":"2025-04-21","cited_by_count":0,"area":"synth"},{"id":"2507.04884","title":"Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions","created":"2025-07-07","cited_by_count":0,"area":"synth"},{"id":"2507.15889","title":"Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing","created":"2025-07-20","cited_by_count":0,"area":"synth"},{"id":"2509.20768","title":"Measuring LLM Sensitivity in Transformer-based Tabular Data Synthesis","created":"2025-09-25","cited_by_count":0,"area":"synth"},{"id":"2509.26340","title":"Memory-Driven Self-Improvement for Decision Making with Large Language Models","created":"2025-09-30","cited_by_count":0,"area":"synth"},{"id":"2510.01229","title":"Enhancing Transformer-Based Rerankers with Synthetic Data and LLM-Based Supervision","created":"2025-09-23","cited_by_count":0,"area":"synth"},{"id":"2511.09539","title":"SynClaimEval: A Framework for Evaluating the Utility of Synthetic Data in Long-Context Claim Verification","created":"2025-11-12","cited_by_count":0,"area":"synth"},{"id":"2602.05106","title":"Data Kernel Perspective Space Performance Guarantees for Synthetic Data from Transformer Models","created":"2026-02-04","cited_by_count":0,"area":"synth"},{"id":"2603.01732","title":"Bootstrapping Embeddings for Low Resource Languages","created":"2026-03-02","cited_by_count":0,"area":"synth"},{"id":"2603.04423","title":"Generating Realistic, Protocol-Compliant Maritime Radio Dialogues using Self-Instruct and Low-Rank Adaptation","created":"2026-02-16","cited_by_count":0,"area":"synth"},{"id":"2603.17220","title":"TharuChat: Bootstrapping Large Language Models for a Low-Resource Language via Synthetic Data and Human Validation","created":"2026-03-17","cited_by_count":0,"area":"synth"},{"id":"2604.12223","title":"LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines","created":"2026-04-14","cited_by_count":0,"area":"synth"},{"id":"2605.07201","title":"PSK@EEUCA 2026: Fine-Tuning Large Language Models with Synthetic Data Augmentation for Multi-Class Toxicity Detection in Gaming Chat","created":"2026-05-08","cited_by_count":0,"area":"synth"},{"id":"2606.04909","title":"BEATS: Bootstrapping E-commerce Attribute Taxonomies for Search through Iterative Human-AI Collaboration","created":"2026-06-03","cited_by_count":0,"area":"synth"},{"id":"2606.29155","title":"OASIF: An Efficient Obfuscation-Aware Self-Improving Framework for LLM-Based Assembly Code Instruction Following and Comprehension","created":"2026-06-28","cited_by_count":0,"area":"synth"},{"id":"2607.22376","title":"A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Books","created":"2026-07-24","cited_by_count":0,"area":"synth"},{"id":"2609.37883","title":"Zero-shot Dependency Parsing with Unsupervised Cross-Lingual Bootstrapping","created":"2026-09-29","cited_by_count":0,"area":"synth"},{"id":"2609.39447","title":"Synthetic Data Characterization via Training Dynamics","created":"2026-09-30","cited_by_count":0,"area":"synth"}],"next_cursor":null}