{"total":23,"rows":[{"id":"2410.12757","title":"StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples","created":"2024-10-16","cited_by_count":35,"area":null},{"id":"2407.12874","title":"SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning","created":"2024-07-16","cited_by_count":32,"area":null},{"id":"2406.08316","title":"Is Programming by Example solved by LLMs?","created":"2024-06-12","cited_by_count":27,"area":null},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2502.04362","title":"LLMs can be easily Confused by Instructional Distractions","created":"2025-02-05","cited_by_count":13,"area":null},{"id":"2502.15419","title":"Beyond Translation: LLM-Based Data Generation for Multilingual Fact-Checking","created":"2025-02-21","cited_by_count":8,"area":null},{"id":"2507.07229","title":"SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2508.21589","title":"Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning","created":"2025-08-29","cited_by_count":7,"area":null},{"id":"2406.15695","title":"SS-GEN: A Social Story Generation Framework with Large Language Models","created":"2024-06-22","cited_by_count":4,"area":null},{"id":"2407.05463","title":"Training Task Experts through Retrieval Based Distillation","created":"2024-07-07","cited_by_count":3,"area":null},{"id":"2512.14562","title":"Polypersona: Persona-Grounded LLM for Synthetic Survey Responses","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2502.15168","title":"mStyleDistance: Multilingual Style Embeddings and their Evaluation","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2504.17203","title":"High-Fidelity And Complex Test Data Generation For Google SQL Code Generation Services","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2509.13047","title":"Multi-Model Synthetic Training for Mission-Critical Small Language Models","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2509.14399","title":"Annotating Training Data for Conditional Semantic Textual Similarity Measurement using Large Language Models","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2512.22603","title":"Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2602.04785","title":"Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generation","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2410.03904","title":"Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2601.03435","title":"The Critical Role of Aspects in Measuring Document Similarity","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2604.12097","title":"Temporal Flattening in LLM-Generated Text: Comparing Human and LLM Writing Trajectories","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.25835","title":"Context-Instrumental Data Distillation for Kubernetes Manifest Generation: Method and Experimental Evaluation","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2609.00184","title":"Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.38799","title":"Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}