{"total":31,"rows":[{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177,"area":null},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108,"area":null},{"id":"2308.09067","title":"Contrasting Linguistic Patterns in Human and LLM-Generated News Text","created":"2023-08-17","cited_by_count":62,"area":null},{"id":"2303.00807","title":"UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers","created":"2023-03-01","cited_by_count":37,"area":null},{"id":"2402.04376","title":"Scaling laws for learning with real and surrogate data","created":"2024-02-06","cited_by_count":27,"area":null},{"id":"2406.05184","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","created":"2024-06-07","cited_by_count":19,"area":null},{"id":"2407.01965","title":"AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2405.17258","title":"$\\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2303.16028","title":"Synthetically generated text for supervised text analysis","created":"2023-03-28","cited_by_count":10,"area":null},{"id":"2402.01712","title":"Socially Aware Synthetic Data Generation for Suicidal Ideation Detection Using Large Language Models","created":"2024-01-25","cited_by_count":10,"area":null},{"id":"2309.12426","title":"Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges","created":"2023-09-21","cited_by_count":9,"area":null},{"id":"2410.20814","title":"NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2301.01228","title":"DMOps: Data Management Operation and Recipes","created":"2023-01-02","cited_by_count":7,"area":null},{"id":"2403.00462","title":"LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues","created":"2024-03-01","cited_by_count":7,"area":null},{"id":"2212.10522","title":"Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2310.15010","title":"Statistical Depth for Ranking and Characterizing Transformer-Based Text Embeddings","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2502.15860","title":"Synthetic vs. Gold: The Role of LLM Generated Labels and Data in Cyberbullying Detection","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2310.10543","title":"ViPE: Visualise Pretty-much Everything","created":"2023-10-16","cited_by_count":3,"area":null},{"id":"2402.14743","title":"Dependency Annotation of Ottoman Turkish with Multilingual BERT","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2503.16031","title":"Deceptive Humor: A Synthetic Multilingual Benchmark Dataset for Bridging Fabricated Claims with Humorous Content","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2406.11115","title":"Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2410.14897","title":"From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2406.05190","title":"Evaluating the Effectiveness of Data Augmentation for Emotion Classification in Low-Resource Settings","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2509.08304","title":"Explainable Semantic Text Relations: A Question-Answering Framework for Comparing Document Content","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2211.02812","title":"Evaluation of Automated Speech Recognition Systems for Conversational Speech: A Linguistic Perspective","created":"2022-11-05","cited_by_count":0,"area":null},{"id":"2407.10582","title":"Boosting Zero-Shot Crosslingual Performance using LLM-Based Augmentations with Effective Data Selection","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2411.02403","title":"A Persuasion-Based Prompt Learning Approach to Improve Smishing Detection through Data Augmentation","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2506.17264","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2508.10000","title":"AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.15801","title":"LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2604.26986","title":"BatteryPass-12K: The First Dataset for the Novel Digital Battery Passport Conformance Task","created":"2026-04-28","cited_by_count":0,"area":null}],"next_cursor":null}