# LastingBench: Defend Benchmarks Against Knowledge Leakage

arXiv: https://arxiv.org/abs/2506.21614 · HTML: https://mlsanity.com/paper/2506.21614/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 57 references that are in the map.
- First posted on arXiv 21 Jun 2025.

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [LiveBench: A Challenging, Contamination-Limited LLM Benchmark](https://mlsanity.com/paper/2406.19314/) (2024)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [SCROLLS: Standardized CompaRison Over Long Language Sequences](https://mlsanity.com/paper/2201.03533/) (2022)
- [Benchmark Data Contamination of Large Language Models: A Survey](https://mlsanity.com/paper/2406.04244/) (2024)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token](https://mlsanity.com/paper/2405.13792/) (2024)
- [Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA](https://mlsanity.com/paper/2406.17419/) (2024)
- [MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation](https://mlsanity.com/paper/2409.05591/) (2024)
- [LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K](https://mlsanity.com/paper/2402.05136/) (2024)
- [VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning](https://mlsanity.com/paper/2505.22019/) (2025)
- [ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents](https://mlsanity.com/paper/2502.18017/) (2025)
- [GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning](https://mlsanity.com/paper/2505.23399/) (2025)
- [AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge](https://mlsanity.com/paper/2412.13670/) (2024)
- [Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration](https://mlsanity.com/paper/2411.17686/) (2024)
- [Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation](https://mlsanity.com/paper/2502.17521/) (2025)
- [A Survey on Data Contamination for Large Language Models](https://mlsanity.com/paper/2502.14425/) (2025)
- [Long2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall](https://mlsanity.com/paper/2410.23000/) (2024)

## Built on by (most cited first, 14 of 14)

- [SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents](https://mlsanity.com/paper/2601.16746/) (2026)
- [Latent Inter-User Difference Modeling for LLM Personalization](https://mlsanity.com/paper/2507.20849/) (2025)
- [Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering](https://mlsanity.com/paper/2601.11255/) (2026)
- [Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding](https://mlsanity.com/paper/2602.01785/) (2026)
- [CTFusion: A CTF-based Benchmark for LLM Agent Evaluation](https://mlsanity.com/paper/2605.11504/) (2026)
- [EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction](https://mlsanity.com/paper/2609.02783/) (2026)
- [ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation](https://mlsanity.com/paper/2604.26923/) (2026)
- [SWE-Pruner Pro: The Coder LLM Already Knows What to Prune](https://mlsanity.com/paper/2607.18213/) (2026)
- [CANDY: Benchmarking LLMs' Limitations and Assistive Potential in Chinese Misinformation Fact-Checking](https://mlsanity.com/paper/2509.03957/) (2025)
- [QuickScope: Certifying Hard Questions in Dynamic LLM Benchmarks](https://mlsanity.com/paper/2604.17842/) (2026)
- [Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification](https://mlsanity.com/paper/2512.00812/) (2025)
- [When Fusion Helps and When It Breaks: View-Aligned Robustness in Same-Source Financial Imaging](https://mlsanity.com/paper/2602.11020/) (2026)
- [GLEAN: Grounded Lightweight Evaluation Anchors for Contamination-Aware Tabular Reasoning](https://mlsanity.com/paper/2603.02212/) (2026)
- [Schr"odinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?](https://mlsanity.com/paper/2609.27891/) (2026)

## Abstract (arXiv)

The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific data. This undermines the validity of benchmark evaluations, as they no longer reflect genuine model capabilities but instead the effects of data leakage. While prior work has focused on detecting such leakage, little attention has been given to mitigating its impact and preserving the long-term utility of benchmarks. In this paper, we introduce LastingBench, a novel framework designed to continuously reinforce and safeguard existing benchmarks against knowledge leakage. LastingBench identifies leakage points in the context through perturbation, then rewrites the leakage points to counterfactual ones-disrupting memorization while preserving the benchmark's original evaluative intent. Evaluations of state-of-the-art QA benchmarks show significant performance gaps, highlighting the efficacy of LastingBench in reducing memorization effects. LastingBench offers a practical and scalable solution to ensure benchmark robustness over time, promoting fairer and more interpretable evaluations of LLMs.