{"total":29,"rows":[{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99,"area":"synth"},{"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":"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":"2502.15654","title":"Machine-generated text detection prevents language model collapse","created":"2025-02-21","cited_by_count":14,"area":"synth"},{"id":"2311.07070","title":"Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations","created":"2023-11-13","cited_by_count":12,"area":"synth"},{"id":"2410.08327","title":"Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains","created":"2024-10-10","cited_by_count":12,"area":"synth"},{"id":"2305.13691","title":"Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering","created":"2023-05-23","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":"2408.02632","title":"SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models","created":"2024-08-05","cited_by_count":9,"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":"2309.06748","title":"CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation","created":"2023-09-13","cited_by_count":6,"area":"synth"},{"id":"2502.08512","title":"Measuring Diversity in Synthetic Datasets","created":"2025-02-12","cited_by_count":5,"area":"synth"},{"id":"2505.06297","title":"Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction","created":"2025-05-07","cited_by_count":5,"area":"synth"},{"id":"2402.10675","title":"German Text Simplification: Finetuning Large Language Models with Semi-Synthetic Data","created":"2024-02-16","cited_by_count":4,"area":"synth"},{"id":"2210.07313","title":"Bootstrapping Multilingual Semantic Parsers using Large Language Models","created":"2022-10-13","cited_by_count":2,"area":"synth"},{"id":"2308.07645","title":"Steering Language Generation: Harnessing Contrastive Expert Guidance and Negative Prompting for Coherent and Diverse Synthetic Data Generation","created":"2023-08-15","cited_by_count":2,"area":"synth"},{"id":"2604.07486","title":"Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation","created":"2026-04-08","cited_by_count":2,"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":"2510.08245","title":"Contrastive Decoding for Synthetic Data Generation in Low-Resource Language Modeling","created":"2025-10-09","cited_by_count":1,"area":"synth"},{"id":"2512.14879","title":"Entropy-Reservoir Bregman Projection: An Information-Geometric Unification of Model Collapse","created":"2025-12-16","cited_by_count":1,"area":"synth"},{"id":"2604.10114","title":"CircuitSynth: Reliable Synthetic Data Generation","created":"2026-04-11","cited_by_count":1,"area":"synth"},{"id":"2605.23054","title":"Model Collapse as Cultural Evolution","created":"2026-05-21","cited_by_count":1,"area":"synth"},{"id":"2606.00282","title":"Synthetic Data from Cross-Domain Events for Large-Scale Recommendation Systems","created":"2026-05-29","cited_by_count":1,"area":"synth"},{"id":"2307.10633","title":"Multi-Method Self-Training: Improving Code Generation With Text, And Vice Versa","created":"2023-07-20","cited_by_count":0,"area":"synth"},{"id":"2603.18428","title":"Adaptive Decoding via Test-Time Policy Learning for Self-Improving Generation","created":"2026-03-19","cited_by_count":0,"area":"synth"},{"id":"2604.07147","title":"Dynamic Context Evolution for Scalable Synthetic Data Generation","created":"2026-04-08","cited_by_count":0,"area":"synth"},{"id":"2605.20602","title":"Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies","created":"2026-05-20","cited_by_count":0,"area":"synth"},{"id":"2609.11146","title":"The Oligarch Barely Steers Model Collapse in Multi-Model Ecosystems","created":"2026-09-10","cited_by_count":0,"area":"synth"}],"next_cursor":null}