Recent claims about the impressive abilities of large language models (LLMs) are often supported by evaluating publicly available benchmarks. Since LLMs train on wide swaths of the internet, this practice raises concerns of data contamination, i.e., evaluating on examples that are explicitly or implicitly included in the training data. Data contamination remains notoriously challenging to measure and mitigate, even with partial attempts like controlled experimentation of training data, canary strings, or embedding similarities. In this work, we conduct the first thorough longitudinal analysis of data contamination in LLMs by using the natural experiment of training cutoffs in GPT models to look at benchmarks released over time. Specifically, we consider two code/mathematical problem-solving datasets, Codeforces and Project Euler, and find statistically significant trends among LLM pass rate vs. GitHub popularity and release date that provide strong evidence of contamination. By open-sourcing our dataset, raw results, and evaluation framework, our work paves the way for rigorous analyses of data contamination in modern models. We conclude with a discussion of best practices and future steps for publicly releasing benchmarks in the age of LLMs that train on webscale data.

翻译：近期关于大型语言模型（LLMs）惊人能力的论断，往往依赖于在公开基准测试上的评估结果。由于LLMs在互联网海量数据上进行训练，这种评估方式引发了数据污染的担忧——即模型进行评估时可能使用了明确或隐含包含在训练数据中的样本。即使已有控制训练数据实验、金丝雀字符串、嵌入相似度等部分应对措施，数据污染的测量与缓解依然极具挑战性。本研究利用GPT模型训练截断期这一自然实验，首次对LLMs的数据污染进行系统性的纵向分析，重点关注随时间发布的基准测试数据。具体而言，我们针对Codeforces和Project Euler这两个编程/数学问题求解数据集，发现LLM通过率与GitHub流行度及发布日期的统计显著趋势，这为数据污染提供了强有力的证据。通过开源我们的数据集、原始结果和评估框架，本研究为现代模型的数据污染严谨分析奠定了基础。最后，我们讨论了在LLMs基于网络规模数据训练的时代，公开基准测试发布的最佳实践与未来方向。