Large Language Models (LLMs) have shown remarkable capabilities in language understanding and generation. Nonetheless, it was also witnessed that LLMs tend to produce inaccurate responses to specific queries. This deficiency can be traced to the tokenization step LLMs must undergo, which is an inevitable limitation inherent to all LLMs. In fact, incorrect tokenization is the critical point that hinders LLMs in understanding the input precisely, thus leading to unsatisfactory output. To demonstrate this flaw of LLMs, we construct an adversarial dataset, named as $\textbf{ADT (Adversarial Dataset for Tokenizer)}$, which draws upon the vocabularies of various open-source LLMs to challenge LLMs' tokenization. ADT consists of two subsets: the manually constructed ADT-Human and the automatically generated ADT-Auto. Our empirical results reveal that our ADT is highly effective on challenging the tokenization of leading LLMs, including GPT-4o, Llama-3, Qwen2.5-max and so on, thus degrading these LLMs' capabilities. Moreover, our method of automatic data generation has been proven efficient and robust, which can be applied to any open-source LLMs. To the best of our knowledge, our study is the first to investigating LLMs' vulnerability in terms of challenging their token segmentation, which will shed light on the subsequent research of improving LLMs' capabilities through optimizing their tokenization process and algorithms.

翻译：大语言模型（LLMs）在语言理解和生成方面展现出卓越的能力。然而，人们也观察到LLMs在面对特定查询时容易产生不准确的回答。这一缺陷可追溯至LLMs必须经历的分词步骤，这是所有LLMs固有的、不可避免的局限性。事实上，错误的分词是阻碍LLMs精确理解输入的关键点，从而导致不理想的输出。为揭示LLMs的这一缺陷，我们构建了一个名为$\textbf{ADT（分词器对抗数据集）}$的对抗性数据集，该数据集利用各类开源LLMs的词汇表来挑战LLMs的分词能力。ADT包含两个子集：人工构建的ADT-Human与自动生成的ADT-Auto。实验结果表明，我们的ADT在挑战包括GPT-4o、Llama-3、Qwen2.5-max等主流LLMs的分词机制方面极为有效，显著削弱了这些模型的性能。此外，我们提出的自动数据生成方法被证明是高效且鲁棒的，可适用于任何开源LLMs。据我们所知，本研究首次从挑战分词切分的角度探究LLMs的脆弱性，这将为后续通过优化分词过程与算法来提升LLMs能力的研究提供重要启示。