{"total":19,"rows":[{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2403.04811","title":"Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models","created":"2024-03-06","cited_by_count":65,"area":null},{"id":"2412.15194","title":"MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark","created":"2024-12-19","cited_by_count":41,"area":null},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38,"area":null},{"id":"2502.14425","title":"A Survey on Data Contamination for Large Language Models","created":"2025-02-20","cited_by_count":35,"area":null},{"id":"2406.14644","title":"Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation","created":"2024-06-20","cited_by_count":30,"area":null},{"id":"2410.18966","title":"Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions","created":"2024-10-24","cited_by_count":26,"area":null},{"id":"2404.00699","title":"A Comprehensive Survey of Contamination Detection Methods in Large Language Models","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2503.13572","title":"VeriContaminated: Assessing LLM-Driven Verilog Coding for Data Contamination","created":"2025-03-17","cited_by_count":12,"area":null},{"id":"2409.19014","title":"FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmark","created":"2024-09-24","cited_by_count":11,"area":null},{"id":"2506.10024","title":"Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models","created":"2025-06-09","cited_by_count":7,"area":null},{"id":"2501.18287","title":"Mining for Species, Locations, Habitats, and Ecosystems from Scientific Papers in Invasion Biology: A Large-Scale Exploratory Study with Large Language Models","created":"2025-01-30","cited_by_count":4,"area":null},{"id":"2504.18474","title":"Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions","created":"2025-04-25","cited_by_count":2,"area":null},{"id":"2511.21218","title":"Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2505.15501","title":"Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2506.12321","title":"Beyond Frequency: The Role of Redundancy in Large Language Model Memorization","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2510.18029","title":"DynaQuery: A Self-Adapting Framework for Querying Structured and Multimodal Data","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.23284","title":"DCMM-SQL: Automated Data-Centric Pipeline and Multi-Model Collaboration Training for Text-to-SQL Model","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2604.17771","title":"SPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks","created":"2026-04-20","cited_by_count":0,"area":null}],"next_cursor":null}