The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination

• URL: http://arxiv.org/abs/2503.16402v1
• Date: Thu, 20 Mar 2025 17:55:04 GMT
• Title: The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination
• Authors: Yifan Sun, Han Wang, Dongbai Li, Gang Wang, Huan Zhang,
• Abstract summary: Benchmark Data Contamination (BDC)-the inclusion of benchmark testing samples in the training set-has raised increasing concerns in Large Language Model (LLM) evaluation.<n>To address this, researchers have proposed various mitigation strategies to update existing benchmarks, including modifying original questions or generating new ones based on them.<n>Previous assessment methods, such as accuracy drop and accuracy matching, focus solely on aggregate accuracy, often leading to incomplete or misleading conclusions.
• Score: 18.05548914181797
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Benchmark Data Contamination (BDC)-the inclusion of benchmark testing samples in the training set-has raised increasing concerns in Large Language Model (LLM) evaluation, leading to falsely inflated performance estimates and undermining evaluation reliability. To address this, researchers have proposed various mitigation strategies to update existing benchmarks, including modifying original questions or generating new ones based on them. However, a rigorous examination of the effectiveness of these mitigation strategies remains lacking. In this paper, we design a systematic and controlled pipeline along with two novel metrics-fidelity and contamination resistance-to provide a fine-grained and comprehensive assessment of existing BDC mitigation strategies. Previous assessment methods, such as accuracy drop and accuracy matching, focus solely on aggregate accuracy, often leading to incomplete or misleading conclusions. Our metrics address this limitation by emphasizing question-level evaluation result matching. Extensive experiments with 10 LLMs, 5 benchmarks, 20 BDC mitigation strategies, and 2 contamination scenarios reveal that no existing strategy significantly improves resistance over the vanilla case (i.e., no benchmark update) across all benchmarks, and none effectively balances fidelity and contamination resistance. These findings underscore the urgent need for designing more effective BDC mitigation strategies. Our code repository is available at https://github.com/ASTRAL-Group/BDC_mitigation_assessment.

Related papers

• Importance Sampling is All You Need: Predict LLM's performance on new benchmark by reusing existing benchmark [38.42021928363628]
  Existing benchmarks face two major challenges: (1) the escalating cost of constructing high-quality test suites and reference solutions, and (2) the increasing risk of data contamination.<n>We propose BIS, a prompt-centric evaluation framework that enables ground-truth-free prediction of LLM performance on code generation tasks.<n>Our framework achieves an average absolute prediction error of 1.1% for code correctness scores, with best- and worst-case errors of 0.3% and 1.9%, respectively.
  arXiv  Detail & Related papers  (2025-08-02T05:34:05Z)
• How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework [8.76693832650115]
  Overestimation in evaluating large language models (LLMs) has become an increasing concern.<n>We propose ArxivRoll, a dynamic evaluation framework inspired by one-time pad encryption in cryptography.
  arXiv  Detail & Related papers  (2025-07-25T12:39:03Z)
• REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once [33.049237516125146]
  We present REST (Reasoning Evaluation through Simultaneous Testing), a stress-testing framework that exposes Large Reasoning Models to multiple problems simultaneously.<n>Our evaluation reveals several striking findings: Even state-of-the-art (SOTA) models like DeepSeek-R1 exhibit substantial performance degradation under stress testing.
  arXiv  Detail & Related papers  (2025-07-14T17:58:47Z)
• Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation [6.4212082894269535]
  We compare existing leakage detection techniques, namely permutation and n-gram-based methods.<n>Our analysis shows that the n-gram method consistently achieves the highest F1-score.<n>We create cleaned versions of MMLU and HellaSwag, and re-evaluate several LLMs.
  arXiv  Detail & Related papers  (2025-05-30T06:37:39Z)
• T2I-Eval-R1: Reinforcement Learning-Driven Reasoning for Interpretable Text-to-Image Evaluation [60.620408007636016]
  We propose T2I-Eval-R1, a novel reinforcement learning framework that trains open-source MLLMs using only coarse-grained quality scores.<n>Our approach integrates Group Relative Policy Optimization into the instruction-tuning process, enabling models to generate both scalar scores and interpretable reasoning chains.
  arXiv  Detail & Related papers  (2025-05-23T13:44:59Z)
• SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event Detection [70.23196257213829]
  We propose a scalable and reliable Semantic-level Evaluation framework for Open domain Event detection.<n>Our proposed framework first constructs a scalable evaluation benchmark that currently includes 564 event types covering 7 major domains.<n>We then leverage large language models (LLMs) as automatic evaluation agents to compute a semantic F1-score, incorporating fine-grained definitions of semantically similar labels.
  arXiv  Detail & Related papers  (2025-03-05T09:37:05Z)
• LLM-Safety Evaluations Lack Robustness [58.334290876531036]
  We argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise.<n>We propose a set of guidelines for reducing noise and bias in evaluations of future attack and defense papers.
  arXiv  Detail & Related papers  (2025-03-04T12:55:07Z)
• MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense [42.56467639172508]
  Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data. We build the first practical benchmark named MIBench for systematic evaluation of model inversion attacks and defenses.
  arXiv  Detail & Related papers  (2024-10-07T16:13:49Z)
• RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework [66.93260816493553]
  This paper introduces RAGEval, a framework designed to assess RAG systems across diverse scenarios.<n>With a focus on factual accuracy, we propose three novel metrics: Completeness, Hallucination, and Irrelevance.<n> Experimental results show that RAGEval outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.
  arXiv  Detail & Related papers  (2024-08-02T13:35:11Z)
• 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)
• 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)
• DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models [4.953092503184905]
  This work proposes DCR, an automated framework for evaluating and improving the consistency of Large Language Models (LLMs) generated texts. We introduce an automatic metric converter (AMC) that translates the output from DCE into an interpretable numeric score. Our approach also substantially reduces nearly 90% of output inconsistencies, showing promise for effective hallucination mitigation.
  arXiv  Detail & Related papers  (2024-01-04T08:34:16Z)
• Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly [79.07074710460012]
  adversarial vulnerability of deep neural networks (DNNs) has drawn great attention. An increasing number of transfer-based methods have been developed to fool black-box DNN models. We establish a transfer-based attack benchmark (TA-Bench) which implements 30+ methods.
  arXiv  Detail & Related papers  (2023-11-02T15:35:58Z)
• Efficient Benchmarking of Language Models [22.696230279151166]
  We present the problem of Efficient Benchmarking, namely, intelligently reducing the costs of LM evaluation without compromising reliability. Using the HELM benchmark as a test case, we investigate how different benchmark design choices affect the computation-reliability trade-off. We propose an evaluation algorithm, that, when applied to the HELM benchmark, leads to dramatic cost savings with minimal loss of benchmark reliability.
  arXiv  Detail & Related papers  (2023-08-22T17:59:30Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)
• Guiding Pseudo-labels with Uncertainty Estimation for Test-Time Adaptation [27.233704767025174]
  Test-Time Adaptation (TTA) is a specific case of Unsupervised Domain Adaptation (UDA) where a model is adapted to a target domain without access to source data. We propose a novel approach for the TTA setting based on a loss reweighting strategy that brings robustness against the noise that inevitably affects the pseudo-labels.
  arXiv  Detail & Related papers  (2023-03-07T10:04:55Z)

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.