mlsanityData to 7 Oct 2026

Benchmark Data Contamination of Large Language Models: A Survey

arXiv 2406.04244 ↗First posted 6 Jun 2024cs.CLcited by 138

Not on the map. Why?

Cited by 32 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The rapid development of Large Language Models (LLMs) like GPT-4, Claude-3, and Gemini has transformed the field of natural language processing. However, it has also resulted in a significant issue known as Benchmark Data Contamination (BDC). This occurs when language models inadvertently incorporate evaluation benchmark information from their training data, leading to inaccurate or unreliable performance during the evaluation phase of the process. This paper reviews the complex challenge of BDC in LLM evaluation and explores alternative assessment methods to mitigate the risks associated with traditional benchmarks. The paper also examines challenges and future directions in mitigating BDC risks, highlighting the complexity of the issue and the need for innovative solutions to ensure the reliability of LLM evaluation in real-world applications.

Key facts. Cited by 138 papers in the map (data through 7 Oct 2026). Builds on 117 of its 164 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

117 of 164 references.

References · 117

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  9. 2020Scaling Laws for Neural Language Modelscited by 6,411
  10. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  11. 2017On Calibration of Modern Neural Networkscited by 4,860
  12. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
38 more
  1. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  2. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2020Extracting Training Data from Large Language Modelscited by 2,144
  5. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  6. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  7. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  8. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  10. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  11. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  12. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  13. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  14. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
  15. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  16. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  17. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  18. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  19. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  20. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 828
  21. 2017Selective Classification for Deep Neural Networkscited by 799
  22. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 738
  23. 2023Extracting Training Data from Diffusion Modelscited by 723
  24. 2022A Survey on In-context Learningcited by 717
  25. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  26. 2020Pre-trained Models for Natural Language Processing: A Surveycited by 504
  27. 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
  28. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 481
  29. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
  30. 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 382
  31. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  32. 2017"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detectioncited by 361
  33. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 359
  34. 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 351
  35. 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 344
  36. 2023NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmarkcited by 339
  37. 2022Deduplicating Training Data Mitigates Privacy Risks in Language Modelscited by 309
  38. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294

50 most cited of 117 All 117 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 18; 2025: 61; 2026: 59.

138 papers.

Sort:

By area:

  1. 2024OLMoE: Open Mixture-of-Experts Language Modelscited by 291
  2. 2025SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?cited by 254
  3. 2024FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AIcited by 227
  4. 2025Preference Leakage: A Contamination Problem in LLM-as-a-judgecited by 119
  5. 2024ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilitiescited by 104
  6. 2025Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluationcited by 57
  7. 2025Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluationcited by 38
  8. 2025A Survey on Data Contamination for Large Language Modelscited by 33
  9. 2025Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoningcited by 33
  10. 2024Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediationcited by 30
  11. 2025Benchmarking Reasoning Robustness in Large Language Modelscited by 30
  12. 2024VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbationcited by 29
38 more
  1. 2024Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptionscited by 26
  2. 2025Social Genome: Grounded Social Reasoning Abilities of Multimodal Modelscited by 24
  3. 2025Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Reportcited by 21
  4. 2024Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oraclecited by 19
  5. 2026Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learnedcited by 18
  6. 2024From Single to Multi: How LLMs Hallucinate in Multi-Document Summarizationcited by 17
  7. 2024How Much Can We Forget about Data Contamination?cited by 14
  8. 2025LastingBench: Defend Benchmarks Against Knowledge Leakagecited by 14
  9. 2025How Contaminated Is Your Benchmark? Quantifying Dataset Leakage in Large Language Models with Kernel Divergencecited by 13
  10. 2025The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contaminationcited by 13
  11. 2025Evaluation Awareness Scales Predictably in Open-Weights Large Language Modelscited by 13
  12. 2025VeriContaminated: Assessing LLM-Driven Verilog Coding for Data Contaminationcited by 12
  13. 2024System 2 thinking in OpenAI's o1-preview model: Near-perfect performance on a mathematics examcited by 10
  14. 2025DCR: Quantifying Data Contamination in LLMs Evaluationcited by 10
  15. 2026SWE-Router: Routing in Multi-turn Agentic Software Engineering Taskscited by 9
  16. 2024The Impact of Copyrighted Material on Large Language Models: A Norwegian Perspectivecited by 8
  17. 2025Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Modelscited by 8
  18. 2025On The Fragility of Benchmark Contamination Detection in Reasoning Modelscited by 8
  19. 2026Riemann-Bench: A Benchmark for Moonshot Mathematicscited by 8
  20. 2024Fine-tuning can Help Detect Pretraining Data from Large Language Modelscited by 7
  21. 2025Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questionscited by 7
  22. 2025Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMscited by 7
  23. 2025RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systemscited by 7
  24. 2025Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarkscited by 7
  25. 2025Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests insteadcited by 7
  26. 2025BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Modelscited by 7
  27. 2024UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Modelscited by 6
  28. 2024MAVEN-Fact: A Large-scale Event Factuality Detection Datasetcited by 6
  29. 2026ClawEnvKit: Automatic Environment Generation for Claw-Like Agentscited by 6
  30. 2026Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AIcited by 6
  31. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 6
  32. 2025Generative AI and Creativity: A Systematic Literature Review and Meta-Analysiscited by 5
  33. 2025Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structurescited by 5
  34. 2025Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluationcited by 5
  35. 2026Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluationcited by 5
  36. 2026Multilingual Reasoning Gym: Multilingual Scaling of Procedural Reasoning Environmentscited by 5
  37. 2026Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wildcited by 5
  38. 2025Multi-Step Reasoning in Korean and the Emergent Miragecited by 4

50 most cited of 138 All 138 (JSON)