{"total":20,"rows":[{"id":"2410.08964","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","created":"2024-10-11","cited_by_count":28,"area":"synth"},{"id":"2401.14698","title":"Under the Surface: Tracking the Artifactuality of LLM-Generated Data","created":"2024-01-26","cited_by_count":24,"area":"synth"},{"id":"2409.16636","title":"Training Language Models to Win Debates with Self-Play Improves Judge Accuracy","created":"2024-09-25","cited_by_count":16,"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":"2405.13326","title":"Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning","created":"2024-05-22","cited_by_count":9,"area":"synth"},{"id":"2407.05474","title":"Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses","created":"2024-07-07","cited_by_count":5,"area":"synth"},{"id":"2506.03558","title":"ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch","created":"2025-06-04","cited_by_count":5,"area":"synth"},{"id":"2606.27226","title":"Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement","created":"2026-06-25","cited_by_count":5,"area":"synth"},{"id":"2608.29856","title":"GenRubric: Self-Evolving Rubric Generation for Scalable LLM Evaluation","created":"2026-08-30","cited_by_count":5,"area":"synth"},{"id":"2509.21451","title":"VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding","created":"2025-09-25","cited_by_count":4,"area":"synth"},{"id":"2507.22930","title":"Protecting Vulnerable Voices: Synthetic Dataset Generation for Self-Disclosure Detection","created":"2025-07-24","cited_by_count":3,"area":"synth"},{"id":"2601.14160","title":"Domain-Adaptation through Synthetic Data: Fine-Tuning Large Language Models for German Law","created":"2026-01-20","cited_by_count":2,"area":"synth"},{"id":"2507.16974","title":"Leveraging Synthetic Data for Question Answering with Multilingual LLMs in the Agricultural Domain","created":"2025-07-22","cited_by_count":1,"area":"synth"},{"id":"2605.08138","title":"DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis","created":"2026-05-02","cited_by_count":1,"area":"synth"},{"id":"2606.08077","title":"Support Vector Rubrics: Closing the Gap Between Self-Generated and Human Rubrics","created":"2026-06-06","cited_by_count":1,"area":"synth"},{"id":"2608.06474","title":"WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader","created":"2026-08-06","cited_by_count":1,"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":"2603.09403","title":"LLM as a Meta-Judge: Synthetic Data for NLP Evaluation Metric Validation","created":"2026-03-10","cited_by_count":0,"area":"synth"},{"id":"2605.27914","title":"Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation Paradigm","created":"2026-05-27","cited_by_count":0,"area":"synth"},{"id":"2607.06160","title":"LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction Synthesis","created":"2026-07-07","cited_by_count":0,"area":"synth"}],"next_cursor":null}