{"total":85,"rows":[{"id":"2406.19314","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","created":"2024-06-27","cited_by_count":262,"area":null},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125,"area":null},{"id":"2404.02936","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","created":"2024-04-03","cited_by_count":103,"area":null},{"id":"2505.15146","title":"lmgame-Bench: How Good are LLMs at Playing Games?","created":"2025-05-21","cited_by_count":55,"area":null},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2411.06176","title":"M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework","created":"2024-11-09","cited_by_count":36,"area":null},{"id":"2410.22821","title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","created":"2024-10-30","cited_by_count":34,"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":"2507.15887","title":"AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2510.18471","title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","created":"2025-10-21","cited_by_count":24,"area":null},{"id":"2508.13180","title":"Search-Time Data Contamination","created":"2025-08-12","cited_by_count":19,"area":null},{"id":"2410.01769","title":"Quantifying Generalization Complexity for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2410.08385","title":"Language model developers should report train-test overlap","created":"2024-10-10","cited_by_count":16,"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":"2505.03427","title":"MedArabiQ: Benchmarking Large Language Models on Arabic Medical Tasks","created":"2025-05-06","cited_by_count":15,"area":null},{"id":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2410.02675","title":"FAN: Fourier Analysis Networks","created":"2024-10-03","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":"2502.11596","title":"LLM Embeddings for Deep Learning on Tabular Data","created":"2025-02-17","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":"2604.14199","title":"PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data","created":"2026-04-03","cited_by_count":12,"area":null},{"id":"2405.15523","title":"The Mosaic Memory of Large Language Models","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2409.18952","title":"RepairBench: Leaderboard of Frontier Models for Program Repair","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2505.23796","title":"Emergent LLM behaviors are observationally equivalent to data leakage","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2506.03231","title":"NetArena: Dynamic Benchmarks for AI Agents in Network Automation","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2506.23706","title":"Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments","created":"2025-06-30","cited_by_count":8,"area":null},{"id":"2511.14045","title":"Auditing Data Membership in Reinforcement Learning With Verifiable Rewards","created":"2025-11-18","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":"2505.15741","title":"Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2506.19399","title":"Automated Detection of Pre-training Text in Black-box LLMs","created":"2025-06-24","cited_by_count":6,"area":null},{"id":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2505.03019","title":"Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2507.21914","title":"Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2509.01082","title":"RefineStat: Efficient Exploration for Probabilistic Program Synthesis","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2601.13240","title":"KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2603.04737","title":"Interactive Benchmarks","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2603.29020","title":"Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2504.04372","title":"Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models","created":"2025-04-06","cited_by_count":4,"area":null},{"id":"2505.13531","title":"AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2512.14391","title":"RePo: Language Models with Context Re-Positioning","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2512.20823","title":"NotSoTiny: A Large, Living Benchmark for RTL Code Generation","created":"2025-12-23","cited_by_count":4,"area":null},{"id":"2604.07650","title":"A Statistical Framework for Auditing Behavioral Dependence and Induced Bias in LLM Judges","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2403.00046","title":"Exploring Data-Efficient Adaptation of Large Language Models for Code Generation","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2504.10359","title":"DICE: A Framework for Dimensional and Contextual Evaluation of Language Models","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2510.08616","title":"LLMs Show Surface-Form Brittleness Under Paraphrase Stress Tests","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2512.06836","title":"Leveraging LLMs to support co-evolution between definitions and instances of textual DSLs","created":"2025-12-07","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":"2605.26161","title":"TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2411.10842","title":"CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit","created":"2024-11-16","cited_by_count":2,"area":null},{"id":"2411.15396","title":"The Decoy Dilemma in Online Medical Information Evaluation: A Comparative Study of Credibility Assessments by LLM and Human Judges","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2501.04510","title":"CGP-Tuning: Structure-Aware Soft Prompt Tuning for Code Vulnerability Detection","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2503.04756","title":"Peeking Behind Closed Doors: Risks of LLM Evaluation by Private Data Curators","created":"2025-02-09","cited_by_count":2,"area":null},{"id":"2505.22759","title":"FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian","created":"2025-05-28","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":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2603.26539","title":"How Open Must Language Models be to Enable Reliable Scientific Inference?","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2604.23593","title":"When AI reviews science: Can we trust the referee?","created":"2026-04-26","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":"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},{"id":"2502.01243","title":"OphthBench: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Ophthalmology","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2502.02573","title":"Are Language Models Up to Sequential Optimization Problems? From Evaluation to a Hegelian-Inspired Enhancement","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2506.06060","title":"Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2507.06056","title":"Data Compressibility Quantifies LLM Memorization","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2508.20468","title":"ConspirED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2510.09717","title":"Provable Training Data Identification for Large Language Models","created":"2025-10-10","cited_by_count":1,"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":"2601.04540","title":"AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet Adaptation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2602.11904","title":"Leveraging LLMs to support co-evolution between definitions and instances of textual DSLs: A Systematic Evaluation","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2602.16481","title":"Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2605.23628","title":"How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness","created":"2026-05-22","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":"2412.11194","title":"Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points","created":"2024-12-15","cited_by_count":0,"area":null},{"id":"2505.08389","title":"Towards Contamination Resistant Benchmarks","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2505.13249","title":"RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Models","created":"2025-05-19","cited_by_count":0,"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":"2506.18213","title":"A Conceptual Framework for AI Capability Evaluations","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2601.13658","title":"Beyond Known Facts: Generating Unseen Temporal Knowledge to Address Data Contamination in LLM Evaluation","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.11674","title":"Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.09696","title":"TemporalDoRA: Temporal PEFT for Robust Surgical Video Question Answering","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.16197","title":"Are Large Language Models Truly Smarter Than Humans?","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.26101","title":"Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2608.05797","title":"Predicting Task Difficulty Without Rollouts","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.14653","title":"Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms","created":"2026-07-31","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}