{"total":46,"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":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"area":null},{"id":"2412.04862","title":"EXAONE 3.5: Series of Large Language Models for Real-world Use Cases","created":"2024-12-06","cited_by_count":53,"area":null},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40,"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":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"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":"2407.07565","title":"On Leakage of Code Generation Evaluation Datasets","created":"2024-07-10","cited_by_count":32,"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":"2406.17681","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","created":"2024-06-25","cited_by_count":29,"area":null},{"id":"2406.13236","title":"Data Contamination Can Cross Language Barriers","created":"2024-06-19","cited_by_count":26,"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":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2406.14394","title":"SEC-QA: A Systematic Evaluation Corpus for Financial QA","created":"2024-06-20","cited_by_count":17,"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":"2407.11470","title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2507.11405","title":"DCR: Quantifying Data Contamination in LLMs Evaluation","created":"2025-07-15","cited_by_count":10,"area":null},{"id":"2602.12413","title":"Soft Contamination Means Benchmarks Test Shallow Generalization","created":"2026-02-12","cited_by_count":8,"area":null},{"id":"2503.02296","title":"Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2510.06296","title":"VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code","created":"2025-10-07","cited_by_count":7,"area":null},{"id":"2407.12220","title":"Questionable practices in machine learning","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2510.09595","title":"LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2502.06655","title":"Unbiased Evaluation of Large Language Models from a Causal Perspective","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2508.17361","title":"Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias","created":"2025-08-24","cited_by_count":3,"area":null},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2604.24703","title":"Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2608.02985","title":"Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2608.13522","title":"Vero: Can AI Agents Build Formally Verified Software Repositories?","created":"2026-08-13","cited_by_count":2,"area":null},{"id":"2510.16022","title":"Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2602.07457","title":"Pull Requests as a Training Signal for Repo-Level Code Editing","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.15485","title":"SecCodeBench-V2 Technical Report","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2605.24079","title":"TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2506.02791","title":"Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2604.14437","title":"LLMs taking shortcuts in test generation: A study with SAP HANA and LevelDB","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.27551","title":"Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.21615","title":"ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.19149","title":"OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.29815","title":"SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.16564","title":"ReqGenX: An Empirical Study of Atomic Decomposition, Artifact Regeneration, and Reconstruction for Legacy SRS Documents","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.18642","title":"Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.10315","title":"Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.12771","title":"Memorization Diagnostics for Code LLMs Should be Scale-Aware","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.18496","title":"MiST: Mid-Training LLMs for Cybersecurity","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.02438","title":"Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}