{"total":63,"rows":[{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939,"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":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187,"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":"2402.10379","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","created":"2024-02-16","cited_by_count":43,"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":"2412.14203","title":"BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement","created":"2024-12-16","cited_by_count":29,"area":"synth"},{"id":"2210.17541","title":"Zero-Shot Text Classification with Self-Training","created":"2022-10-31","cited_by_count":26,"area":"synth"},{"id":"2404.04298","title":"SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses","created":"2024-04-04","cited_by_count":26,"area":"synth"},{"id":"2510.01631","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","created":"2025-10-02","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":"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":"2402.02285","title":"SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking","created":"2024-02-03","cited_by_count":17,"area":"synth"},{"id":"2405.19846","title":"Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model","created":"2024-05-30","cited_by_count":16,"area":"synth"},{"id":"2402.12368","title":"A synthetic data approach for domain generalization of NLI models","created":"2024-02-19","cited_by_count":15,"area":"synth"},{"id":"2406.05892","title":"Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language Models","created":"2024-06-09","cited_by_count":14,"area":"synth"},{"id":"2409.02098","title":"CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation","created":"2024-09-03","cited_by_count":14,"area":"synth"},{"id":"2410.18588","title":"Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data","created":"2024-10-24","cited_by_count":12,"area":"synth"},{"id":"2112.02212","title":"Hierarchical Neural Data Synthesis for Semantic Parsing","created":"2021-12-04","cited_by_count":11,"area":"synth"},{"id":"2301.11489","title":"Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation","created":"2023-01-27","cited_by_count":10,"area":"synth"},{"id":"2409.00121","title":"BELT-2: Bootstrapping EEG-to-Language representation alignment for multi-task brain decoding","created":"2024-08-28","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":"2404.02422","title":"Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data","created":"2024-04-03","cited_by_count":7,"area":"synth"},{"id":"2405.11162","title":"LG AI Research & KAIST at EHRSQL 2024: Self-Training Large Language Models with Pseudo-Labeled Unanswerable Questions for a Reliable Text-to-SQL System on EHRs","created":"2024-05-18","cited_by_count":7,"area":"synth"},{"id":"2410.14655","title":"Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens","created":"2024-10-18","cited_by_count":7,"area":"synth"},{"id":"2605.26097","title":"Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay","created":"2026-05-25","cited_by_count":7,"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":"2405.03845","title":"Self-Improving Customer Review Response Generation Based on LLMs","created":"2024-05-06","cited_by_count":5,"area":"synth"},{"id":"2502.17957","title":"On Synthetic Data Strategies for Domain-Specific Generative Retrieval","created":"2025-02-25","cited_by_count":5,"area":"synth"},{"id":"2509.02040","title":"Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation","created":"2025-09-02","cited_by_count":5,"area":"synth"},{"id":"2406.18078","title":"Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction","created":"2024-06-26","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":"2506.00649","title":"GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction","created":"2025-05-31","cited_by_count":4,"area":"synth"},{"id":"2306.03315","title":"Few Shot Rationale Generation using Self-Training with Dual Teachers","created":"2023-06-05","cited_by_count":3,"area":"synth"},{"id":"2310.01119","title":"Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models","created":"2023-10-02","cited_by_count":3,"area":"synth"},{"id":"2504.09643","title":"Iterative Self-Training for Code Generation via Reinforced Re-Ranking","created":"2025-04-13","cited_by_count":3,"area":"synth"},{"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":"2307.04601","title":"InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information Retrieval","created":"2023-07-10","cited_by_count":2,"area":"synth"},{"id":"2405.14212","title":"Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data","created":"2024-05-23","cited_by_count":2,"area":"synth"},{"id":"2407.11504","title":"Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval","created":"2024-07-16","cited_by_count":2,"area":"synth"},{"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":"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":"2604.11290","title":"Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation","created":"2026-04-13","cited_by_count":1,"area":"synth"},{"id":"2605.04127","title":"Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities","created":"2026-05-05","cited_by_count":1,"area":"synth"},{"id":"2609.04511","title":"LentEx: Generalizable Latent Entity Extraction via Synthetic Data and Instruction-Tuned LLMs","created":"2026-09-03","cited_by_count":1,"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":"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":"2509.20768","title":"Measuring LLM Sensitivity in Transformer-based Tabular Data Synthesis","created":"2025-09-25","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":"2601.22146","title":"FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale","created":"2026-01-29","cited_by_count":0,"area":"synth"},{"id":"2602.00665","title":"Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation","created":"2026-01-31","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":"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":"2605.20279","title":"The Economics of Model Collapse: Equilibrium, Welfare, and Optimal Provenance Subsidies in Synthetic Data Markets","created":"2026-05-19","cited_by_count":0,"area":"synth"},{"id":"2607.27379","title":"HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs","created":"2026-07-29","cited_by_count":0,"area":"synth"},{"id":"2608.24263","title":"Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing","created":"2026-08-25","cited_by_count":0,"area":"synth"}],"next_cursor":null}