{"total":93,"rows":[{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"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":"2409.19839","title":"ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities","created":"2024-09-30","cited_by_count":110,"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":"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":"2406.17681","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","created":"2024-06-25","cited_by_count":29,"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":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23,"area":null},{"id":"2411.08324","title":"Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle","created":"2024-11-13","cited_by_count":19,"area":null},{"id":"2410.13961","title":"From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization","created":"2024-10-17","cited_by_count":17,"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":"2410.03249","title":"How Much Can We Forget about Data Contamination?","created":"2024-10-04","cited_by_count":14,"area":null},{"id":"2506.21614","title":"LastingBench: Defend Benchmarks Against Knowledge Leakage","created":"2025-06-21","cited_by_count":14,"area":null},{"id":"2509.13333","title":"Evaluation Awareness Scales Predictably in Open-Weights Large Language Models","created":"2025-09-10","cited_by_count":14,"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":"2507.11405","title":"DCR: Quantifying Data Contamination in LLMs Evaluation","created":"2025-07-15","cited_by_count":10,"area":null},{"id":"2410.10880","title":"Fine-tuning can Help Detect Pretraining Data from Large Language Models","created":"2024-10-09","cited_by_count":8,"area":null},{"id":"2412.09460","title":"The Impact of Copyrighted Material on Large Language Models: A Norwegian Perspective","created":"2024-12-12","cited_by_count":8,"area":null},{"id":"2503.12072","title":"Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models","created":"2025-03-15","cited_by_count":8,"area":null},{"id":"2604.06802","title":"Riemann-Bench: A Benchmark for Moonshot Mathematics","created":"2026-04-08","cited_by_count":8,"area":null},{"id":"2604.18543","title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","created":"2026-04-20","cited_by_count":8,"area":null},{"id":"2507.17747","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2507.23009","title":"Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead","created":"2025-07-30","cited_by_count":7,"area":null},{"id":"2406.16382","title":"UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2407.15352","title":"MAVEN-Fact: A Large-scale Event Factuality Detection Dataset","created":"2024-07-22","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":"2505.17241","title":"Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2505.20429","title":"PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2603.10793","title":"Multilingual Reasoning Gym: Multilingual Scaling of Procedural Reasoning Environments","created":"2026-03-11","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":"2603.29403","title":"Security in LLM-as-a-Judge: A Comprehensive SoK","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2503.04840","title":"Framing the Game: How Context Shapes LLM Decision-Making","created":"2025-03-05","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":"2507.19909","title":"The Impact of Fine-tuning Large Language Models on Automated Program Repair","created":"2025-07-26","cited_by_count":3,"area":null},{"id":"2509.09705","title":"The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks","created":"2025-09-05","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":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","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":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2503.21646","title":"Unlocking the Potential of Past Research: Using Generative AI to Reconstruct Healthcare Simulation Models","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2504.06324","title":"From Stability to Inconsistency: A Study of Moral Preferences in LLMs","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2504.17198","title":"Automatically Generating Rules of Malicious Software Packages via Large Language Model","created":"2025-04-24","cited_by_count":2,"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":"2508.05452","title":"LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2510.08569","title":"ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2511.09139","title":"MACEval: A Multi-Agent Continual Evaluation Network for Large Models","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2511.10691","title":"Evaluating from Benign to Dynamic Adversarial: A Squid Game for Large Language Models","created":"2025-11-12","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":"2606.03650","title":"CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2607.18269","title":"Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles","created":"2026-05-26","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":"2609.01552","title":"Can LLMs Discover Scientific Laws in Real and Parallel Worlds?","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2410.11265","title":"In-Context Learning for Long-Context Sentiment Analysis on Infrastructure Project Opinions","created":"2024-10-15","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":"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":"2511.21591","title":"On the Limits of Innate Planning in Large Language Models","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2601.22720","title":"AEGIS: White-Box Attack Path Generation using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2604.26048","title":"BioGraphletQA: Knowledge-Anchored Generation of Complex QA Datasets","created":"2026-04-28","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":"2607.15263","title":"Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2505.12983","title":"An Empirical Study of Many-to-Many Summarization with Large Language Models","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2507.06434","title":"Deprecating Benchmarks: Criteria and Framework","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2507.13302","title":"The Generative Energy Arena (GEA): Incorporating Energy Awareness in Large Language Model (LLM) Human Evaluations","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2508.06060","title":"LLMs for Resource Allocation: A Participatory Budgeting Approach to Inferring Preferences","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2508.12096","title":"STEM: Efficient Relative Capability Evaluation of LLMs through Structured Transition Samples","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2509.09960","title":"Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2512.02043","title":"Mirror, Mirror on the Wall -- Which is the Best Model of Them All?","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.24826","title":"Video and Language Alignment in 2D Systems for 3D Multi-object Scenes with Multi-Information Derivative-Free Control","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2602.13217","title":"VeRA: Renewing Reasoning Benchmarks with Executable Specifications","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2603.16642","title":"When AI Navigates the Fog of War","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.19711","title":"Can Large Language Models Reliably Correct Errors in Low-Resource ASR? A Contamination-Aware Case Study on West Frisian","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.21543","title":"Provable Joint Decontamination for Benchmarking Multiple Large Language Models","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.30916","title":"Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.18539","title":"TS-Fault: Benchmarking Time Series Forecasters Against Structural Faults","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.19788","title":"CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.02996","title":"On the missing benchmarks layer and a potential solution","created":"2026-08-04","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":"2608.25623","title":"Using profiles of cognitive capability to assess AI suitability for workplace tasks","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.29463","title":"Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2608.29543","title":"Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.10357","title":"A Later Test Set Is Not a New Domain: Pretraining Familiarity Survives a Contamination-Free Hold-Out","created":"2026-09-09","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":"2609.36726","title":"Can AI Scientists Change Their Minds? Prior-Evidence Conflict in Synthetic Universes","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04569","title":"From Transformers to Weighted Automata: Towards the Verification of Large Language Models","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.04888","title":"No Hindsight for LLM Fact-Checkers: Measuring Leakage Channels in Misinformation Detection","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.09296","title":"The AI Evaluation Ecosystem","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10597","title":"Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.16152","title":"WildTrace: Evaluating Training Data Detection in Realistic Large-Scale LLM Post-Training","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}