{"total":15,"rows":[{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303,"area":null},{"id":"2406.11813","title":"How Do Large Language Models Acquire Factual Knowledge During Pretraining?","created":"2024-06-17","cited_by_count":90,"area":null},{"id":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2308.12477","title":"American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers","created":"2023-08-24","cited_by_count":11,"area":null},{"id":"2305.08286","title":"A Language Model of Java Methods with Train/Test Deduplication","created":"2023-05-15","cited_by_count":7,"area":null},{"id":"2406.09490","title":"Newswire: A Large-Scale Structured Database of a Century of Historical News","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2306.17810","title":"A Massive Scale Semantic Similarity Dataset of Historical English","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2309.00789","title":"LinkTransformer: A Unified Package for Record Linkage with Transformer Language Models","created":"2023-09-02","cited_by_count":4,"area":null},{"id":"2407.15339","title":"Deep Learning for Economists","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2311.17264","title":"RETSim: Resilient and Efficient Text Similarity","created":"2023-11-28","cited_by_count":2,"area":null},{"id":"2406.15593","title":"News Deja Vu: Connecting Past and Present with Semantic Search","created":"2024-06-21","cited_by_count":2,"area":null},{"id":"2505.06993","title":"Technical Report: Quantifying and Analyzing the Generalization Power of a DNN","created":"2025-05-11","cited_by_count":2,"area":null},{"id":"2502.11866","title":"Southern Newswires: A Large-Scale Study of Mid-Century Wire Content Beyond the Front Page","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2609.03350","title":"From Zero to Hero: An Open LLM Ecosystem for Armenian","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}