{"total":58,"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":"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":"2407.03282","title":"LLM Internal States Reveal Hallucination Risk Faced With a Query","created":"2024-07-03","cited_by_count":82,"area":null},{"id":"2405.20267","title":"Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions","created":"2024-05-30","cited_by_count":42,"area":"agents"},{"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":"2402.02823","title":"Evading Data Contamination Detection for Language Models is (too) Easy","created":"2024-02-05","cited_by_count":30,"area":null},{"id":"2403.02990","title":"Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges","created":"2024-03-05","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":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2404.07584","title":"UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs","created":"2024-04-11","cited_by_count":24,"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":"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":"2410.09247","title":"Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts","created":"2024-10-11","cited_by_count":14,"area":null},{"id":"2502.20258","title":"LLM as a Broken Telephone: Iterative Generation Distorts Information","created":"2025-02-27","cited_by_count":12,"area":null},{"id":"2406.04197","title":"DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning","created":"2024-06-06","cited_by_count":11,"area":"lr"},{"id":"2506.06112","title":"Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness","created":"2025-06-06","cited_by_count":11,"area":"safety"},{"id":"2412.04318","title":"The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation","created":"2024-12-05","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":"2511.04934","title":"Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding","created":"2025-11-07","cited_by_count":9,"area":"safety"},{"id":"2402.00861","title":"Evaluating Large Language Models for Generalization and Robustness via Data Compression","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2603.02540","title":"A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities","created":"2026-03-03","cited_by_count":5,"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":"2509.04304","title":"Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2506.04142","title":"Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis","created":"2025-06-04","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":"2601.05478","title":"The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence","created":"2026-01-09","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":"2603.11228","title":"Markovian Generation Chains in Large Language Models","created":"2026-03-11","cited_by_count":3,"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":"2506.02037","title":"FinS-Pilot: A Benchmark for Online Financial RAG System","created":"2025-05-31","cited_by_count":2,"area":"rag"},{"id":"2508.10444","title":"DiFaR: Enhancing Multimodal Misinformation Detection with Diverse, Factual, and Relevant Rationales","created":"2025-08-14","cited_by_count":2,"area":"mllm"},{"id":"2509.23362","title":"Dual-Space Smoothness for Robust and Balanced LLM Unlearning","created":"2025-09-27","cited_by_count":2,"area":"safety"},{"id":"2510.26285","title":"Language Models Learn Universal Representations of Numbers and Here's Why You Should Care","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2605.16776","title":"Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning","created":"2026-05-16","cited_by_count":2,"area":"safety"},{"id":"2608.22948","title":"What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation","created":"2026-08-24","cited_by_count":2,"area":null},{"id":"2403.14562","title":"Agentic AI: The Era of Semantic Decoding","created":"2024-03-21","cited_by_count":1,"area":"agents"},{"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":"2505.22018","title":"Improving Continual Pre-training Through Seamless Data Packing","created":"2025-05-28","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":"2511.06160","title":"Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles","created":"2025-11-08","cited_by_count":1,"area":"lr"},{"id":"2604.15203","title":"MADE: A Living Benchmark for Multi-Label Text Classification with Uncertainty Quantification of Medical Device Adverse Events","created":"2026-04-16","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":"2605.26133","title":"Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications","created":"2026-05-21","cited_by_count":1,"area":"safety"},{"id":"2607.28887","title":"To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2504.20018","title":"MINT: Multi-Vector Search Index Tuning","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2601.06747","title":"FinForge: Semi-Synthetic Financial Benchmark Generation","created":"2026-01-11","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":"2603.16642","title":"When AI Navigates the Fog of War","created":"2026-03-17","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":"2606.07996","title":"MC-PDD: Masked Corpus-Level Pretraining Data Detection for Black-Box Large Language Models","created":"2026-06-06","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":"2609.10092","title":"RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases","created":"2026-09-09","cited_by_count":0,"area":"agents"},{"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":"2610.16133","title":"Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}