{"total":22,"rows":[{"id":"2502.08468","title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","created":"2025-02-12","cited_by_count":49,"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":"2505.14423","title":"Scaling Low-Resource MT via Synthetic Data Generation with LLMs","created":"2025-05-20","cited_by_count":14,"area":"synth"},{"id":"2110.09570","title":"A Data Bootstrapping Recipe for Low Resource Multilingual Relation Classification","created":"2021-10-18","cited_by_count":8,"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":"2510.09051","title":"Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation","created":"2025-10-10","cited_by_count":5,"area":"synth"},{"id":"2412.18707","title":"Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Data","created":"2024-12-24","cited_by_count":3,"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":"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":"2511.10338","title":"BhashaKritika: Building Synthetic Pretraining Data at Scale for Indic Languages","created":"2025-11-13","cited_by_count":2,"area":"synth"},{"id":"2601.16278","title":"Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification","created":"2026-01-22","cited_by_count":2,"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":"2510.06143","title":"RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets","created":"2025-10-07","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":"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":"2601.03792","title":"VietMed-MCQ: A Consistency-Filtered Data Synthesis Framework for Vietnamese Traditional Medicine Evaluation","created":"2026-01-07","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":"2603.17220","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":"2604.15675","title":"C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignment","created":"2026-04-17","cited_by_count":0,"area":"synth"},{"id":"2606.18389","title":"Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation","created":"2026-06-16","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}