{"total":133,"rows":[{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2402.15938","title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models","created":"2024-02-24","cited_by_count":122,"area":null},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114,"area":null},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106,"area":null},{"id":"2401.06059","title":"Investigating Data Contamination for Pre-training Language Models","created":"2024-01-11","cited_by_count":91,"area":null},{"id":"2406.06565","title":"MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures","created":"2024-06-03","cited_by_count":74,"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":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2402.16775","title":"A Comprehensive Evaluation of Quantization Strategies for Large Language Models","created":"2024-02-26","cited_by_count":48,"area":null},{"id":"2311.06233","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","created":"2023-11-10","cited_by_count":47,"area":null},{"id":"2412.13670","title":"AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge","created":"2024-12-18","cited_by_count":44,"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":"2406.15053","title":"PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data","created":"2024-06-21","cited_by_count":37,"area":null},{"id":"2404.06209","title":"Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models","created":"2024-04-09","cited_by_count":36,"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":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"area":null},{"id":"2506.05334","title":"Search Arena: Analyzing Search-Augmented LLMs","created":"2025-06-05","cited_by_count":34,"area":null},{"id":"2405.16281","title":"ConStat: Performance-Based Contamination Detection in Large Language Models","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2411.03923","title":"Evaluation data contamination in LLMs: how do we measure it and (when) does it matter?","created":"2024-11-06","cited_by_count":32,"area":null},{"id":"2402.02823","title":"Evading Data Contamination Detection for Language Models is (too) Easy","created":"2024-02-05","cited_by_count":30,"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":"2408.08808","title":"Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge","created":"2024-08-16","cited_by_count":30,"area":null},{"id":"2410.02677","title":"CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming","created":"2024-10-03","cited_by_count":30,"area":null},{"id":"2412.10064","title":"Text2Cypher: Bridging Natural Language and Graph Databases","created":"2024-12-13","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":"2404.02823","title":"Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models","created":"2024-04-03","cited_by_count":27,"area":null},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"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":"2403.04814","title":"Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks","created":"2024-03-07","cited_by_count":25,"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":"2409.20222","title":"Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models","created":"2024-09-30","cited_by_count":20,"area":null},{"id":"2405.04520","title":"NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts","created":"2024-05-07","cited_by_count":19,"area":null},{"id":"2406.13990","title":"Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation","created":"2024-06-20","cited_by_count":19,"area":null},{"id":"2407.21077","title":"Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models","created":"2024-07-29","cited_by_count":19,"area":null},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2409.10566","title":"Eureka: Evaluating and Understanding Large Foundation Models","created":"2024-09-13","cited_by_count":18,"area":null},{"id":"2502.04153","title":"UltraIF: Advancing Instruction Following from the Wild","created":"2025-02-06","cited_by_count":18,"area":null},{"id":"2501.17858","title":"Improving Your Model Ranking on Chatbot Arena by Vote Rigging","created":"2025-01-29","cited_by_count":17,"area":null},{"id":"2502.13252","title":"Multilingual Language Model Pretraining using Machine-translated Data","created":"2025-02-18","cited_by_count":17,"area":null},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2502.00678","title":"How Contaminated Is Your Benchmark? Quantifying Dataset Leakage in Large Language Models with Kernel Divergence","created":"2025-02-02","cited_by_count":15,"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":"2402.13125","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","created":"2024-02-20","cited_by_count":14,"area":null},{"id":"2410.03249","title":"How Much Can We Forget about Data Contamination?","created":"2024-10-04","cited_by_count":14,"area":null},{"id":"2605.12673","title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","created":"2026-05-12","cited_by_count":14,"area":null},{"id":"2501.18771","title":"Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation","created":"2025-01-30","cited_by_count":13,"area":null},{"id":"2502.07445","title":"Forget What You Know about LLMs Evaluations -- LLMs are Like a Chameleon","created":"2025-02-11","cited_by_count":13,"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":"2407.08716","title":"A Taxonomy for Data Contamination in Large Language Models","created":"2024-07-11","cited_by_count":11,"area":null},{"id":"2412.15184","title":"Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2602.08003","title":"Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection","created":"2026-02-08","cited_by_count":11,"area":null},{"id":"2507.11405","title":"DCR: Quantifying Data Contamination in LLMs Evaluation","created":"2025-07-15","cited_by_count":10,"area":null},{"id":"2406.16714","title":"AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2408.03281","title":"StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation","created":"2024-08-06","cited_by_count":9,"area":null},{"id":"2410.10998","title":"WILT: A Multi-Turn, Memorization-Robust Inductive Logic Benchmark for LLMs","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2504.20964","title":"OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2510.27055","title":"Detecting Data Contamination in LLMs via In-Context Learning","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2602.12413","title":"Soft Contamination Means Benchmarks Test Shallow Generalization","created":"2026-02-12","cited_by_count":8,"area":null},{"id":"2405.06331","title":"LMD3: Language Model Data Density Dependence","created":"2024-05-10","cited_by_count":7,"area":null},{"id":"2505.18102","title":"CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2510.21900","title":"Deep Literature Survey Automation with an Iterative Workflow","created":"2025-10-24","cited_by_count":7,"area":null},{"id":"2406.18326","title":"PaCoST: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models","created":"2024-06-26","cited_by_count":6,"area":null},{"id":"2407.04065","title":"On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards","created":"2024-07-04","cited_by_count":6,"area":null},{"id":"2502.17259","title":"Detecting Benchmark Contamination Through Watermarking","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2507.19219","title":"How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework","created":"2025-07-25","cited_by_count":6,"area":null},{"id":"2510.07248","title":"Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2401.06935","title":"MiTTenS: A Dataset for Evaluating Gender Mistranslation","created":"2024-01-13","cited_by_count":5,"area":null},{"id":"2401.12246","title":"Orion-14B: Open-source Multilingual Large Language Models","created":"2024-01-20","cited_by_count":5,"area":null},{"id":"2502.14911","title":"Batayan: A Filipino NLP benchmark for evaluating Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2503.05049","title":"Dynamic-KGQA: A Scalable Framework for Generating Adaptive Question Answering Datasets","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2503.10673","title":"ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2504.12562","title":"ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2605.10448","title":"Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2407.12220","title":"Questionable practices in machine learning","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2409.12746","title":"Bilingual Evaluation of Language Models on General Knowledge in University Entrance Exams with Minimal Contamination","created":"2024-09-19","cited_by_count":3,"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":"2506.00482","title":"Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2508.07180","title":"Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2509.14448","title":"VCBench: Benchmarking LLMs in Venture Capital","created":"2025-09-17","cited_by_count":3,"area":null},{"id":"2510.06730","title":"PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2511.18889","title":"CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2601.08847","title":"Scalable and Reliable Evaluation of AI Knowledge Retrieval Systems: RIKER and the Coherent Simulated Universe","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2601.20858","title":"When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation","created":"2026-01-28","cited_by_count":3,"area":null},{"id":"2603.08371","title":"Leaderboard Incentives: Model Rankings under Strategic Post-Training","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2605.26161","title":"TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2406.03428","title":"HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2410.16186","title":"Contamination Report for Multilingual Benchmarks","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2412.04947","title":"C$^2$LEVA: Toward Comprehensive and Contamination-Free Language Model Evaluation","created":"2024-12-06","cited_by_count":2,"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":"2510.05026","title":"Idiom Understanding as a Tool to Measure the Dialect Gap","created":"2025-10-06","cited_by_count":2,"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":"2605.19999","title":"LLM Benchmark Datasets Should Be Contamination-Resistant","created":"2026-05-19","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":"2403.19340","title":"Dataverse: Open-Source ETL (Extract, Transform, Load) Pipeline for Large Language Models","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2410.15005","title":"CAP: Data Contamination Detection via Consistency Amplification","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2501.13983","title":"AdEval: Alignment-based Dynamic Evaluation to Mitigate Data Contamination in Large Language Models","created":"2025-01-23","cited_by_count":1,"area":null}],"next_cursor":"100"}