Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation

• URL: http://arxiv.org/abs/2505.24263v1
• Date: Fri, 30 May 2025 06:37:39 GMT
• Title: Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation
• Authors: Naila Shafirni Hidayat, Muhammad Dehan Al Kautsar, Alfan Farizki Wicaksono, Fajri Koto,
• Abstract summary: 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.
• Score: 6.4212082894269535
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The performance of large language models (LLMs) continues to improve, as reflected in rising scores on standard benchmarks. However, the lack of transparency around training data raises concerns about potential overlap with evaluation sets and the fairness of reported results. Although prior work has proposed methods for detecting data leakage, these approaches primarily focus on identifying outliers and have not been evaluated under controlled simulated leakage conditions. In this work, we compare existing leakage detection techniques, namely permutation and n-gram-based methods, under a continual pretraining setup that simulates real-world leakage scenarios, and additionally explore a lightweight method we call semi-half question. Although semi-half offers a low-cost alternative, our analysis shows that the n-gram method consistently achieves the highest F1-score. We also refine these techniques to support instance-level detection and reduce computational overhead. Leveraging the best-performing method, we create cleaned versions of MMLU and HellaSwag, and re-evaluate several LLMs. Our findings present a practical path toward more reliable and transparent evaluations, and we recommend contamination checks as a standard step before releasing benchmark results.

Related papers

• Can LLM-Driven Hard Negative Sampling Empower Collaborative Filtering? Findings and Potentials [9.668242919588199]
  Hard negative samples can accelerate model convergence and optimize decision boundaries.<n>This paper introduces the concept of Semantic Negative Sampling.<n>We propose a framework called HNLMRec, based on fine-tuning LLMs supervised by collaborative signals.
  arXiv  Detail & Related papers  (2025-04-07T04:39:45Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• A Survey on Data Contamination for Large Language Models [12.431575579432458]
  Large Language Models (LLMs) have demonstrated significant progress in various areas, such as text generation and code synthesis.<n>The reliability of performance evaluation has come under scrutiny due to data contamination.
  arXiv  Detail & Related papers  (2025-02-20T10:23:27Z)
• Achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models [56.92178753201331]
  We tackle average-reward infinite-horizon POMDPs with an unknown transition model.<n>We present a novel and simple estimator that overcomes this barrier.
  arXiv  Detail & Related papers  (2025-01-30T22:29:41Z)
• Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method [108.56493934296687]
  We introduce a divergence-based calibration method, inspired by the divergence-from-randomness concept, to calibrate token probabilities for pretraining data detection.<n>We have developed a Chinese-language benchmark, PatentMIA, to assess the performance of detection approaches for LLMs on Chinese text.
  arXiv  Detail & Related papers  (2024-09-23T07:55:35Z)
• On Speeding Up Language Model Evaluation [48.51924035873411]
  We propose an $textitadaptive$ approach to explore this space.<n>We lean on multi-armed bandits to sequentially identify the next (method, validation sample)-pair to evaluate.<n>We show that it can identify the top-performing method using only 5-15% of the typical resources.
  arXiv  Detail & Related papers  (2024-07-08T17:48:42Z)
• 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)
• Regression-aware Inference with LLMs [52.764328080398805]
  We show that an inference strategy can be sub-optimal for common regression and scoring evaluation metrics. We propose alternate inference strategies that estimate the Bayes-optimal solution for regression and scoring metrics in closed-form from sampled responses.
  arXiv  Detail & Related papers  (2024-03-07T03:24:34Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• Investigating Data Contamination in Modern Benchmarks for Large Language Models [27.479260572913724]
  Recent observations have underscored a disparity between the inflated benchmark scores and the actual performance of LLMs. We study data contamination by proposing two methods tailored for both open-source and proprietary LLMs. We find that certain commercial LLMs could surprisingly guess the missing option in various test sets.
  arXiv  Detail & Related papers  (2023-11-16T11:03:04Z)
• 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)
• Re-Evaluating LiDAR Scene Flow for Autonomous Driving [80.37947791534985]
  Popular benchmarks for self-supervised LiDAR scene flow have unrealistic rates of dynamic motion, unrealistic correspondences, and unrealistic sampling patterns. We evaluate a suite of top methods on a suite of real-world datasets. We show that despite the emphasis placed on learning, most performance gains are caused by pre- and post-processing steps.
  arXiv  Detail & Related papers  (2023-04-04T22:45:50Z)

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.