{"total":17,"rows":[{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2412.06724","title":"AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark","created":"2024-12-09","cited_by_count":24,"area":null},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"area":null},{"id":"2405.10040","title":"SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation","created":"2024-05-16","cited_by_count":13,"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":"2502.14644","title":"LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2407.05463","title":"Training Task Experts through Retrieval Based Distillation","created":"2024-07-07","cited_by_count":3,"area":null},{"id":"2412.06136","title":"AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2505.20264","title":"We Need to Measure Data Diversity in NLP -- Better and Broader","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.00277","title":"Hierarchical Level-Wise News Article Clustering via Multilingual Matryoshka Embeddings","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2601.11575","title":"Concept Attractors in LLMs and their Applications","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2408.09585","title":"On the Necessity of World Knowledge for Mitigating Missing Labels in Extreme Classification","created":"2024-08-18","cited_by_count":0,"area":null},{"id":"2508.09544","title":"SYNAPSE-G: Bridging Large Language Models and Graph Learning for Rare Event Classification","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2510.11944","title":"TopoAlign: A Framework for Aligning Code to Math via Topological Decomposition","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2512.06239","title":"LOCUS: A System and Method for Low-Cost Customization for Universal Specialization","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2602.17465","title":"Entropy-Based Data Selection for Language Models","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2608.24268","title":"ROBE: Reversed-Order-Biased-Experts for Extracting Extreme Long-tail Events from Historical Texts","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}