{"total":15,"rows":[{"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":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23,"area":null},{"id":"2503.16402","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2510.07740","title":"AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2602.16747","title":"LiveClin: A Live Clinical Benchmark without Leakage","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2509.20909","title":"LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2411.00045","title":"A Novel Psychometrics-Based Approach to Developing Professional Competency Benchmark for Large Language Models","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2608.16391","title":"Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.00062","title":"RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.27176","title":"LeakScale: Estimating the Causal Effect of Benchmark Exposure","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.27510","title":"Uncheatable Eval: Dynamic Compression-Based Evaluation of Language Models","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.00164","title":"Metric-Construction Coupling Inflates Measured Synthetic Dialect Recovery","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}