# AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge

arXiv: https://arxiv.org/abs/2412.13670 · HTML: https://mlsanity.com/paper/2412.13670/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 61 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Builds on (most cited first, 30 of 40)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions](https://mlsanity.com/paper/2305.14795/) (2023)
- [RealTime QA: What's the Answer Right Now?](https://mlsanity.com/paper/2207.13332/) (2022)
- [Data Contamination: From Memorization to Exploitation](https://mlsanity.com/paper/2203.08242/) (2022)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [Rethinking Benchmark and Contamination for Language Models with Rephrased Samples](https://mlsanity.com/paper/2311.04850/) (2023)
- [Don't Make Your LLM an Evaluation Benchmark Cheater](https://mlsanity.com/paper/2311.01964/) (2023)
- [A Careful Examination of Large Language Model Performance on Grade School Arithmetic](https://mlsanity.com/paper/2405.00332/) (2024)
- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://mlsanity.com/paper/2305.12744/) (2023)
- [Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks](https://mlsanity.com/paper/2305.10160/) (2023)
- [StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models](https://mlsanity.com/paper/2205.11388/) (2022)
- [Investigating Data Contamination for Pre-training Language Models](https://mlsanity.com/paper/2401.06059/) (2024)
- [Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap](https://mlsanity.com/paper/2402.19450/) (2024)
- [DynaSent: A Dynamic Benchmark for Sentiment Analysis](https://mlsanity.com/paper/2012.15349/) (2020)
- [Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation](https://mlsanity.com/paper/2306.05783/) (2023)
- [Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning](https://mlsanity.com/paper/2211.12878/) (2022)

## Built on by (most cited first, 30 of 44)

- [Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation](https://mlsanity.com/paper/2502.17521/) (2025)
- [Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks](https://mlsanity.com/paper/2504.18838/) (2025)
- [Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings](https://mlsanity.com/paper/2506.04997/) (2025)
- [MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering](https://mlsanity.com/paper/2412.15540/) (2024)
- [The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination](https://mlsanity.com/paper/2503.16402/) (2025)
- [Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning](https://mlsanity.com/paper/2502.14356/) (2025)
- [LastingBench: Defend Benchmarks Against Knowledge Leakage](https://mlsanity.com/paper/2506.21614/) (2025)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [Unsupervised Hallucination Detection by Inspecting Reasoning Processes](https://mlsanity.com/paper/2509.10004/) (2025)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base](https://mlsanity.com/paper/2502.12591/) (2025)
- [LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence](https://mlsanity.com/paper/2512.04578/) (2025)
- [Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation](https://mlsanity.com/paper/2504.13054/) (2025)
- [DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors](https://mlsanity.com/paper/2505.23001/) (2025)
- [Lean Meets Theoretical Computer Science: Scalable Synthesis of Theorem Proving Challenges in Formal-Informal Pairs](https://mlsanity.com/paper/2508.15878/) (2025)
- [Test of Time: Rethinking Temporal Signal of Benchmark Contamination](https://mlsanity.com/paper/2509.00072/) (2025)
- [VCBench: Benchmarking LLMs in Venture Capital](https://mlsanity.com/paper/2509.14448/) (2025)
- [CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation](https://mlsanity.com/paper/2511.18889/) (2025)
- [The Ever-Evolving Science Exam](https://mlsanity.com/paper/2507.16514/) (2025)
- [LLM Benchmark Datasets Should Be Contamination-Resistant](https://mlsanity.com/paper/2605.19999/) (2026)
- [ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment](https://mlsanity.com/paper/2606.00644/) (2026)
- [Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores](https://mlsanity.com/paper/2608.02985/) (2026)
- [GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks](https://mlsanity.com/paper/2608.03764/) (2026)
- [SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation](https://mlsanity.com/paper/2505.14419/) (2025)
- [MatheMagic: Generating Dynamic Mathematics Benchmarks Robust to Memorization](https://mlsanity.com/paper/2510.05962/) (2025)
- [Individualized Cognitive Simulation in Large Language Models: Evaluating Different Cognitive Representation Methods](https://mlsanity.com/paper/2510.20252/) (2025)
- [DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry](https://mlsanity.com/paper/2510.22340/) (2025)
- [How Do Large Language Models Learn Concepts During Continual Pre-Training?](https://mlsanity.com/paper/2601.03570/) (2026)
- [Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents](https://mlsanity.com/paper/2601.21699/) (2026)
- [From 0-Order Selection to 2-Order Judgment: Combinatorial Hardening Exposes Compositional Failures in Frontier LLMs](https://mlsanity.com/paper/2605.07268/) (2026)

## Abstract (arXiv)

Data contamination hinders fair LLM evaluation by introducing test data into newer models' training sets. Existing studies solve this challenge by updating benchmarks with newly collected data. However, they fail to guarantee contamination-free evaluation as the newly collected data may contain pre-existing knowledge, and their benchmark updates rely on intensive human labor. To address these issues, we in this paper propose AntiLeak-Bench, an automated anti-leakage benchmarking framework. Instead of simply using newly collected data, we construct samples with explicitly new knowledge absent from LLMs' training sets, which thus ensures strictly contamination-free evaluation. We further design a fully automated workflow to build and update our benchmark without human labor. This significantly reduces the cost of benchmark maintenance to accommodate emerging LLMs. Through extensive experiments, we highlight that data contamination likely exists before LLMs' cutoff time and demonstrate AntiLeak-Bench effectively overcomes this challenge.