On The Fragility of Benchmark Contamination Detection in Reasoning Models

• URL: http://arxiv.org/abs/2510.02386v1
• Date: Tue, 30 Sep 2025 21:40:54 GMT
• Title: On The Fragility of Benchmark Contamination Detection in Reasoning Models
• Authors: Han Wang, Haoyu Li, Brian Ko, Huan Zhang,
• Abstract summary: Leaderboards for LRMs have turned evaluation into a competition, incentivizing developers to optimize directly on benchmark suites.<n>A shortcut to achieving higher rankings is to incorporate evaluation benchmarks into the training data, thereby yielding inflated performance, known as benchmark contamination.<n>We find that evading contamination detections for LRMs is alarmingly easy.
• Score: 20.455365567122985
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Leaderboards for LRMs have turned evaluation into a competition, incentivizing developers to optimize directly on benchmark suites. A shortcut to achieving higher rankings is to incorporate evaluation benchmarks into the training data, thereby yielding inflated performance, known as benchmark contamination. Surprisingly, our studies find that evading contamination detections for LRMs is alarmingly easy. We focus on the two scenarios where contamination may occur in practice: (I) when the base model evolves into LRM via SFT and RL, we find that contamination during SFT can be originally identified by contamination detection methods. Yet, even a brief GRPO training can markedly conceal contamination signals that most detection methods rely on. Further empirical experiments and theoretical analysis indicate that PPO style importance sampling and clipping objectives are the root cause of this detection concealment, indicating that a broad class of RL methods may inherently exhibit similar concealment capability; (II) when SFT contamination with CoT is applied to advanced LRMs as the final stage, most contamination detection methods perform near random guesses. Without exposure to non-members, contaminated LRMs would still have more confidence when responding to those unseen samples that share similar distributions to the training set, and thus, evade existing memorization-based detection methods. Together, our findings reveal the unique vulnerability of LRMs evaluations: Model developers could easily contaminate LRMs to achieve inflated leaderboards performance while leaving minimal traces of contamination, thereby strongly undermining the fairness of evaluation and threatening the integrity of public leaderboards. This underscores the urgent need for advanced contamination detection methods and trustworthy evaluation protocols tailored to LRMs.

Related papers

• When Benchmarks Leak: Inference-Time Decontamination for LLMs [4.071875179293035]
  DeconIEP operates entirely during evaluation by applying small, bounded perturbations in the input embedding space.<n>We propose DeconIEP, a decontamination framework that operates entirely during evaluation by applying small, bounded perturbations in the input embedding space.
  arXiv  Detail & Related papers  (2026-01-27T08:19:40Z)
• Contamination Detection for VLMs using Multi-Modal Semantic Perturbation [73.76465227729818]
  Open-source Vision-Language Models (VLMs) have achieved state-of-the-art performance on benchmark tasks.<n>Pretraining corpora raise a critical concern for both practitioners and users: inflated performance due to test-set leakage.<n>We show that existing detection approaches either fail outright or exhibit inconsistent behavior.<n>We propose a novel simple yet effective detection method based on multi-modal semantic perturbation.
  arXiv  Detail & Related papers  (2025-11-05T18:59:52Z)
• Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models [30.267708813420587]
  Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs)<n>This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance.<n>We propose Self-Critique as a specialized contamination detection method for RL post-training.
  arXiv  Detail & Related papers  (2025-10-10T10:58:50Z)
• Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis [43.58944424023784]
  We aim to tackle contamination by analyzing the mechanisms of contaminated models themselves.<n>We propose a novel method for identifying shortcut neurons through comparative and causal analysis.<n> Experiments validate the effectiveness of our approach in mitigating contamination.
  arXiv  Detail & Related papers  (2025-06-04T16:33:44Z)
• Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM [53.05486269607166]
  multimodal large language models (MLLMs) have significantly enhanced performance across benchmarks.<n>Existing detection methods for unimodal large language models (LLMs) are inadequate for MLLMs due to multimodal data complexity and multi-phase training.<n>We analyze multimodal data contamination using our analytical framework, MM-Detect, which defines two contamination categories-unimodal and cross-modal.
  arXiv  Detail & Related papers  (2024-11-06T10:44:15Z)
• PaCoST: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models [41.772263447213234]
  Large language models (LLMs) are known to be trained on vast amounts of data, which may unintentionally or intentionally include data from commonly used benchmarks.<n>This inclusion can lead to cheatingly high scores on model leaderboards, yet result in disappointing performance in real-world applications.<n>We introduce PaCoST, a Paired Confidence Significance Testing to effectively detect benchmark contamination in LLMs.
  arXiv  Detail & Related papers  (2024-06-26T13:12:40Z)
• A Comprehensive Survey of Contamination Detection Methods in Large Language Models [68.10605098856087]
  With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges.<n>LLMs' performance may not be reliable anymore, as the high performance may be at least partly due to their previous exposure to the data.<n>This limitation jeopardizes real capability improvement in the field of NLP, yet there remains a lack of methods on how to efficiently detect contamination.
  arXiv  Detail & Related papers  (2024-03-31T14:32:02Z)
• Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models [42.958880063727996]
  CDD stands for Contamination Detection via output Distribution for LLMs. To mitigate the impact of data contamination in evaluation, we also present TED: Trustworthy Evaluation via output Distribution.
  arXiv  Detail & Related papers  (2024-02-24T23:54:41Z)
• KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models [53.84677081899392]
  KIEval is a Knowledge-grounded Interactive Evaluation framework for large language models. It incorporates an LLM-powered "interactor" role for the first time to accomplish a dynamic contamination-resilient evaluation. Extensive experiments on seven leading LLMs across five datasets validate KIEval's effectiveness and generalization.
  arXiv  Detail & Related papers  (2024-02-23T01:30:39Z)
• Rethinking Benchmark and Contamination for Language Models with Rephrased Samples [49.18977581962162]
  Large language models are increasingly trained on all the data ever produced by humans. Many have raised concerns about the trustworthiness of public benchmarks due to potential contamination in pre-training or fine-tuning datasets.
  arXiv  Detail & Related papers  (2023-11-08T17:35:20Z)
• Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection [81.07346419422605]
  Anomaly detection aims at identifying deviant samples from the normal data distribution. Contrastive learning has provided a successful way to sample representation that enables effective discrimination on anomalies. We propose a novel hierarchical semi-supervised contrastive learning framework, for contamination-resistant anomaly detection.
  arXiv  Detail & Related papers  (2022-07-24T18:49:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.