调查大型语言模型现代基准测试中的数据污染问题
Investigating Data Contamination in Modern Benchmarks for Large Language Models
AI总结：
针对LLM基准数据污染问题，本文提出检索重叠检测与TS-Guessing协议，发现商业模型可高概率猜中缺失选项，表明需更稳健的评估基准。
摘要：
近期观察凸显了大型语言模型（LLM）虚高的基准测试分数与实际性能之间的差距，引发了人们对评估基准可能受到污染的担忧。对于闭源模型以及某些缺乏训练数据透明度的开源模型而言，这一问题尤为关键。本文通过提出两种同时适用于开源和专有LLM的方法来研究数据污染。我们首先引入一个基于检索的系统，用于探究评估基准与预训练语料库之间潜在的重叠。我们进一步提出一种名为测试集插槽猜测（Testset Slot Guessing，TS-Guessing）的新型调查协议，该协议同时适用于开源和专有模型。该方法包括在多项选择题中遮蔽一个错误答案，并提示模型填补空缺；此外，它还包括在评估示例中隐藏一个不太可能出现的词，并要求模型将其生成出来。我们发现，某些商业LLM竟能在各种测试集中猜出缺失的选项。具体而言，在TruthfulQA基准测试中，我们发现当提供基准中的额外元数据时，LLM表现出显著的性能提升。此外，在MMLU基准测试中，ChatGPT和GPT-4在猜测基准测试数据中缺失选项时的精确匹配率分别达到52%和57%。我们希望这些结果能够凸显本领域对更稳健的评估方法和基准测试的需求。
英文摘要：
Recent observations have underscored a disparity between the inflated benchmark scores and the actual performance of LLMs, raising concerns about potential contamination of evaluation benchmarks. This issue is especially critical for closed-source models and certain open-source models where training data transparency is lacking. In this paper we study data contamination by proposing two methods tailored for both open-source and proprietary LLMs. We first introduce a retrieval-based system to explore potential overlaps between evaluation benchmarks and pretraining corpora. We further present a novel investigation protocol named \textbf{T}estset \textbf{S}lot Guessing (\textit{TS-Guessing}), applicable to both open and proprietary models. This approach entails masking a wrong answer in a multiple-choice question and prompting the model to fill in the gap. Additionally, it involves obscuring an unlikely word in an evaluation example and asking the model to produce it. We find that certain commercial LLMs could surprisingly guess the missing option in various test sets. Specifically, in the TruthfulQA benchmark, we find that LLMs exhibit notable performance improvement when provided with additional metadata in the benchmark. Further, in the MMLU benchmark, ChatGPT and GPT-4 demonstrated an exact match rate of 52\% and 57\%, respectively, in guessing the missing options in benchmark test data. We hope these results underscore the need for more robust evaluation methodologies and benchmarks in the field.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
